Manaal Faruqui

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al. · allen-ai, amazon-science

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

Satyapriya Krishna, Kalpesh Krishna, Anhad Mohananey et al. · deepmind, harvard

Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require LLMs to understand user queries, retrieve relevant information, and synthesize coherent and accurate responses. Given the increasing real-world deployment of such systems, comprehensive evaluation becomes crucial. To this end, we propose FRAMES (Factuality, Retrieval, And reasoning MEasurement Set), a high-quality evaluation dataset designed to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers. While previous work has provided datasets and benchmarks to evaluate these abilities in isolation, FRAMES offers a unified framework that provides a clearer picture of LLM performance in end-to-end RAG scenarios. Our dataset comprises challenging multi-hop questions that require the integration of information from multiple sources. We present baseline results demonstrating that even state-of-the-art LLMs struggle with this task, achieving 0.40 accuracy with no retrieval. The accuracy is significantly improved with our proposed multi-step retrieval pipeline, achieving an accuracy of 0.66 (>50% improvement). We hope our work will help bridge evaluation gaps and assist in developing more robust and capable RAG systems.

Pei Zhou, Aman Madaan, Srividya Pranavi Potharaju et al. · cmu

"Thinking is for Doing." Humans can infer other people's mental states from observations--an ability called Theory-of-Mind (ToM)--and subsequently act pragmatically on those inferences. Existing question answering benchmarks such as ToMi ask models questions to make inferences about beliefs of characters in a story, but do not test whether models can then use these inferences to guide their actions. We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenarios. Experiments on T4D demonstrate that LLMs such as GPT-4 and PaLM 2 seemingly excel at tracking characters' beliefs in stories, but they struggle to translate this capability into strategic action. Our analysis reveals the core challenge for LLMs lies in identifying the implicit inferences about mental states without being explicitly asked about as in ToMi, that lead to choosing the correct action in T4D. To bridge this gap, we introduce a zero-shot prompting framework, Foresee and Reflect (FaR), which provides a reasoning structure that encourages LLMs to anticipate future challenges and reason about potential actions. FaR boosts GPT-4's performance from 50% to 71% on T4D, outperforming other prompting methods such as Chain-of-Thought and Self-Ask. Moreover, FaR generalizes to diverse out-of-distribution story structures and scenarios that also require ToM inferences to choose an action, consistently outperforming other methods including few-shot in-context learning.

Pranjal Aggarwal, Aman Madaan, Ankit Anand et al. · cmu

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and performance remains challenging. In this work, we present Automix, an approach that strategically routes queries to larger LMs, based on the approximate correctness of outputs from a smaller LM. Central to Automix are two key technical contributions. First, it has a few-shot self-verification mechanism, which estimates the reliability of its own outputs without requiring extensive training. Second, given that self-verification can be noisy, it employs a POMDP based router that can effectively select an appropriately sized model, based on answer confidence. Experiments across five language models and five challenging datasets show that Automix consistently surpasses strong baselines, reducing computational cost by over 50% for comparable performance.

Tu Vu, Kalpesh Krishna, Salaheddin Alzubi et al.

As large language models (LLMs) advance, it becomes more challenging to reliably evaluate their output due to the high costs of human evaluation. To make progress towards better LLM autoraters, we introduce FLAMe, a family of Foundational Large Autorater Models. FLAMe is trained on our large and diverse collection of 100+ quality assessment tasks comprising 5M+ human judgments, curated and standardized using publicly released human evaluations from previous research. FLAMe significantly improves generalization to a wide variety of held-out tasks, outperforming LLMs trained on proprietary data like GPT-4 and Claude-3 on many tasks. We show that FLAMe can also serve as a powerful starting point for further downstream fine-tuning, using reward modeling evaluation as a case study (FLAMe-RM). Notably, on RewardBench, our FLAMe-RM-24B model (with an accuracy of 87.8%) is the top-performing generative model trained exclusively on permissively licensed data, outperforming both GPT-4-0125 (85.9%) and GPT-4o (84.7%). Additionally, we explore a more computationally efficient approach using a novel tail-patch fine-tuning strategy to optimize our FLAMe multitask mixture for reward modeling evaluation (FLAMe-Opt-RM), offering competitive RewardBench performance while requiring approximately 25x less training datapoints. Overall, our FLAMe variants outperform all popular proprietary LLM-as-a-Judge models we consider across 8 out of 12 autorater evaluation benchmarks, encompassing 53 quality assessment tasks, including RewardBench and LLM-AggreFact. Finally, our analysis reveals that FLAMe is significantly less biased than these LLM-as-a-Judge models on the CoBBLEr autorater bias benchmark, while effectively identifying high-quality responses for code generation.

Shuo-yiin Chang, Guru Prakash, Zelin Wu et al.

In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query.However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations. Toavoid repeating a hotword, we propose a streaming end-to-end(E2E) intended query detector that identifies the utterancesdirected towards the device and filters out other utterancesnot directed towards device. The proposed approach incor-porates the intended query detector into the E2E model thatalready folds different components of the speech recognitionpipeline into one neural network.The E2E modeling onspeech decoding and intended query detection also allows us todeclare a quick intended query detection based on early partialrecognition result, which is important to decrease latencyand make the system responsive. We demonstrate that theproposed E2E approach yields a 22% relative improvement onequal error rate (EER) for the detection accuracy and 600 mslatency improvement compared with an independent intendedquery detector. In our experiment, the proposed model detectswhether the user is talking to the device with a 8.7% EERwithin 1.4 seconds of median latency after user starts speaking.

Ayush Kaushal, Aditya Gupta, Shyam Upadhyay et al.

A naive application of state-of-the-art bidirectional encoders for streaming sequence tagging would require encoding each token from scratch for each new token in an incremental streaming input (like transcribed speech). The lack of re-usability of previous computation leads to a higher number of Floating Point Operations (or FLOPs) and higher number of unnecessary label flips. Increased FLOPs consequently lead to higher wall-clock time and increased label flipping leads to poorer streaming performance. In this work, we present a Hybrid Encoder with Adaptive Restart (HEAR) that addresses these issues while maintaining the performance of bidirectional encoders over the offline (or complete) inputs while improving performance on streaming (or incomplete) inputs. HEAR has a Hybrid unidirectional-bidirectional encoder architecture to perform sequence tagging, along with an Adaptive Restart Module (ARM) to selectively guide the restart of bidirectional portion of the encoder. Across four sequence tagging tasks, HEAR offers FLOP savings in streaming settings upto 71.1% and also outperforms bidirectional encoders for streaming predictions by upto +10% streaming exact match.

Yun He, Wenzhe Li, Hejia Zhang et al.

Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF (we will release this benchmark soon), a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs ability to follow complex, multi-turn, and system-level instructions. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems.

Gemini Team, Petko Georgiev, Ving Ian Lei et al. · deepmind, mila

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed Infini-attention. The Infini-attention incorporates a compressive memory into the vanilla attention mechanism and builds in both masked local attention and long-term linear attention mechanisms in a single Transformer block. We demonstrate the effectiveness of our approach on long-context language modeling benchmarks, 1M sequence length passkey context block retrieval and 500K length book summarization tasks with 1B and 8B LLMs. Our approach introduces minimal bounded memory parameters and enables fast streaming inference for LLMs.

Lianhui Qin, Aditya Gupta, Shyam Upadhyay et al.

Everyday conversations require understanding everyday events, which in turn, requires understanding temporal commonsense concepts interwoven with those events. Despite recent progress with massive pre-trained language models (LMs) such as T5 and GPT-3, their capability of temporal reasoning in dialogs remains largely under-explored. In this paper, we present the first study to investigate pre-trained LMs for their temporal reasoning capabilities in dialogs by introducing a new task and a crowd-sourced English challenge set, TIMEDIAL. We formulate TIME-DIAL as a multiple-choice cloze task with over 1.1K carefully curated dialogs. Empirical results demonstrate that even the best performing models struggle on this task compared to humans, with 23 absolute points of gap in accuracy. Furthermore, our analysis reveals that the models fail to reason about dialog context correctly; instead, they rely on shallow cues based on existing temporal patterns in context, motivating future research for modeling temporal concepts in text and robust contextual reasoning about them. The dataset is publicly available at: https://github.com/google-research-datasets/timedial.

Aditya Gupta, Jiacheng Xu, Shyam Upadhyay et al.

Disfluencies is an under-studied topic in NLP, even though it is ubiquitous in human conversation. This is largely due to the lack of datasets containing disfluencies. In this paper, we present a new challenge question answering dataset, Disfl-QA, a derivative of SQuAD, where humans introduce contextual disfluencies in previously fluent questions. Disfl-QA contains a variety of challenging disfluencies that require a more comprehensive understanding of the text than what was necessary in prior datasets. Experiments show that the performance of existing state-of-the-art question answering models degrades significantly when tested on Disfl-QA in a zero-shot setting.We show data augmentation methods partially recover the loss in performance and also demonstrate the efficacy of using gold data for fine-tuning. We argue that we need large-scale disfluency datasets in order for NLP models to be robust to them. The dataset is publicly available at: https://github.com/google-research-datasets/disfl-qa.

Graham Neubig, Chris Dyer, Yoav Goldberg et al.

We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives. In DyNet's dynamic declaration strategy, computation graph construction is mostly transparent, being implicitly constructed by executing procedural code that computes the network outputs, and the user is free to use different network structures for each input. Dynamic declaration thus facilitates the implementation of more complicated network architectures, and DyNet is specifically designed to allow users to implement their models in a way that is idiomatic in their preferred programming language (C++ or Python). One challenge with dynamic declaration is that because the symbolic computation graph is defined anew for every training example, its construction must have low overhead. To achieve this, DyNet has an optimized C++ backend and lightweight graph representation. Experiments show that DyNet's speeds are faster than or comparable with static declaration toolkits, and significantly faster than Chainer, another dynamic declaration toolkit. DyNet is released open-source under the Apache 2.0 license and available at http://github.com/clab/dynet.

Shengyu Feng, Yun He, Shuang Ma et al.

Reinforcement learning (RL) has recently proven effective at scaling chain-of-thought (CoT) reasoning in large language models on tasks with verifiable answers. However, extending RL to more general non-verifiable tasks, typically in the format of human preference pairs, remains both challenging and underexplored. In this work, we propose Dual-Weighted Reinforcement Learning (DWRL), a new framework for preference modeling that integrates CoT reasoning with the Bradley-Terry (BT) model via a dual-weighted RL objective that preserves preference-modeling inductive bias. DWRL approximates the maximum-likelihood objective of the BT model with two complementary weights: an instance-wise misalignment weight, which emphasizes under-trained pairs misaligned with human preference, and a group-wise (self-normalized) conditional preference score, which promotes promising thoughts. In this paper, we apply DWRL to preference modeling by training generative preference models (GPMs) to first generate a thought and then predict the human preference score. Across multiple benchmarks and model scales (Llama3 and Qwen2.5), DWRL consistently outperforms both GPM baselines and scalar models, while producing coherent, interpretable thoughts. In summary, our results position DWRL as a general framework for reasoning-enhanced preference learning beyond verifiable tasks.

Gemini Team, Rohan Anil, Sebastian Borgeaud et al.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Manaal Faruqui, Dilek Hakkani-Tür

As more users across the world are interacting with dialog agents in their daily life, there is a need for better speech understanding that calls for renewed attention to the dynamics between research in automatic speech recognition (ASR) and natural language understanding (NLU). We briefly review these research areas and lay out the current relationship between them. In light of the observations we make in this paper, we argue that (1) NLU should be cognizant of the presence of ASR models being used upstream in a dialog system's pipeline, (2) ASR should be able to learn from errors found in NLU, (3) there is a need for end-to-end datasets that provide semantic annotations on spoken input, (4) there should be stronger collaboration between ASR and NLU research communities.

Ankur P. Parikh, Xuezhi Wang, Sebastian Gehrmann et al.

We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. To obtain generated targets that are natural but also faithful to the source table, we introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. We present systematic analyses of our dataset and annotation process as well as results achieved by several state-of-the-art baselines. While usually fluent, existing methods often hallucinate phrases that are not supported by the table, suggesting that this dataset can serve as a useful research benchmark for high-precision conditional text generation.

Zewei Chu, Mingda Chen, Jing Chen et al.

We present a large-scale dataset for the task of rewriting an ill-formed natural language question to a well-formed one. Our multi-domain question rewriting MQR dataset is constructed from human contributed Stack Exchange question edit histories. The dataset contains 427,719 question pairs which come from 303 domains. We provide human annotations for a subset of the dataset as a quality estimate. When moving from ill-formed to well-formed questions, the question quality improves by an average of 45 points across three aspects. We train sequence-to-sequence neural models on the constructed dataset and obtain an improvement of 13.2% in BLEU-4 over baseline methods built from other data resources. We release the MQR dataset to encourage research on the problem of question rewriting.

Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar et al.

The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have emerged about the interpretability of attention weights (Jain & Wallace, 2019; Vig & Belinkov, 2019). Amid such confusion arises the need to understand attention mechanism more systematically. In this work, we attempt to fill this gap by giving a comprehensive explanation which justifies both kinds of observations (i.e., when is attention interpretable and when it is not). Through a series of experiments on diverse NLP tasks, we validate our observations and reinforce our claim of interpretability of attention through manual evaluation.

Bhuwan Dhingra, Manaal Faruqui, Ankur Parikh et al.

Automatically constructed datasets for generating text from semi-structured data (tables), such as WikiBio, often contain reference texts that diverge from the information in the corresponding semi-structured data. We show that metrics which rely solely on the reference texts, such as BLEU and ROUGE, show poor correlation with human judgments when those references diverge. We propose a new metric, PARENT, which aligns n-grams from the reference and generated texts to the semi-structured data before computing their precision and recall. Through a large scale human evaluation study of table-to-text models for WikiBio, we show that PARENT correlates with human judgments better than existing text generation metrics. We also adapt and evaluate the information extraction based evaluation proposed by Wiseman et al (2017), and show that PARENT has comparable correlation to it, while being easier to use. We show that PARENT is also applicable when the reference texts are elicited from humans using the data from the WebNLG challenge.

Hao Peng, Ankur P. Parikh, Manaal Faruqui et al.

We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as "soft templates," which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text generation. Empirical results show that this model achieves strong performance and outperforms comparable baselines.

Christo Kirov, Ryan Cotterell, John Sylak-Glassman et al.

The Universal Morphology UniMorph project is a collaborative effort to improve how NLP handles complex morphology across the world's languages. The project releases annotated morphological data using a universal tagset, the UniMorph schema. Each inflected form is associated with a lemma, which typically carries its underlying lexical meaning, and a bundle of morphological features from our schema. Additional supporting data and tools are also released on a per-language basis when available. UniMorph is based at the Center for Language and Speech Processing (CLSP) at Johns Hopkins University in Baltimore, Maryland and is sponsored by the DARPA LORELEI program. This paper details advances made to the collection, annotation, and dissemination of project resources since the initial UniMorph release described at LREC 2016. lexical resources} }

Jan A. Botha, Manaal Faruqui, John Alex et al.

Split and rephrase is the task of breaking down a sentence into shorter ones that together convey the same meaning. We extract a rich new dataset for this task by mining Wikipedia's edit history: WikiSplit contains one million naturally occurring sentence rewrites, providing sixty times more distinct split examples and a ninety times larger vocabulary than the WebSplit corpus introduced by Narayan et al. (2017) as a benchmark for this task. Incorporating WikiSplit as training data produces a model with qualitatively better predictions that score 32 BLEU points above the prior best result on the WebSplit benchmark.

Manaal Faruqui, Ellie Pavlick, Ian Tenney et al.

We release a corpus of 43 million atomic edits across 8 languages. These edits are mined from Wikipedia edit history and consist of instances in which a human editor has inserted a single contiguous phrase into, or deleted a single contiguous phrase from, an existing sentence. We use the collected data to show that the language generated during editing differs from the language that we observe in standard corpora, and that models trained on edits encode different aspects of semantics and discourse than models trained on raw, unstructured text. We release the full corpus as a resource to aid ongoing research in semantics, discourse, and representation learning.

Manaal Faruqui, Dipanjan Das

Understanding search queries is a hard problem as it involves dealing with "word salad" text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-wellformed categories and report an accuracy of 70.7% on the test set. We also show that our classifier can be used to improve the performance of neural sequence-to-sequence models for generating questions for reading comprehension.

Ryan Cotterell, Christo Kirov, John Sylak-Glassman et al.

The CoNLL-SIGMORPHON 2017 shared task on supervised morphological generation required systems to be trained and tested in each of 52 typologically diverse languages. In sub-task 1, submitted systems were asked to predict a specific inflected form of a given lemma. In sub-task 2, systems were given a lemma and some of its specific inflected forms, and asked to complete the inflectional paradigm by predicting all of the remaining inflected forms. Both sub-tasks included high, medium, and low-resource conditions. Sub-task 1 received 24 system submissions, while sub-task 2 received 3 system submissions. Following the success of neural sequence-to-sequence models in the SIGMORPHON 2016 shared task, all but one of the submissions included a neural component. The results show that high performance can be achieved with small training datasets, so long as models have appropriate inductive bias or make use of additional unlabeled data or synthetic data. However, different biasing and data augmentation resulted in disjoint sets of inflected forms being predicted correctly, suggesting that there is room for future improvement.

Yulia Tsvetkov, Manaal Faruqui, Chris Dyer

We introduce QVEC-CCA--an intrinsic evaluation metric for word vector representations based on correlations of learned vectors with features extracted from linguistic resources. We show that QVEC-CCA scores are an effective proxy for a range of extrinsic semantic and syntactic tasks. We also show that the proposed evaluation obtains higher and more consistent correlations with downstream tasks, compared to existing approaches to intrinsic evaluation of word vectors that are based on word similarity.

Yulia Tsvetkov, Manaal Faruqui, Wang Ling et al.

We use Bayesian optimization to learn curricula for word representation learning, optimizing performance on downstream tasks that depend on the learned representations as features. The curricula are modeled by a linear ranking function which is the scalar product of a learned weight vector and an engineered feature vector that characterizes the different aspects of the complexity of each instance in the training corpus. We show that learning the curriculum improves performance on a variety of downstream tasks over random orders and in comparison to the natural corpus order.

Yulia Tsvetkov, Sunayana Sitaram, Manaal Faruqui et al.

We introduce polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to be predicted. We apply these to the problem of modeling phone sequences---a domain in which universal symbol inventories and cross-linguistically shared feature representations are a natural fit. Intrinsic evaluation on held-out perplexity, qualitative analysis of the learned representations, and extrinsic evaluation in two downstream applications that make use of phonetic features show (i) that polyglot models better generalize to held-out data than comparable monolingual models and (ii) that polyglot phonetic feature representations are of higher quality than those learned monolingually.

Manaal Faruqui, Yulia Tsvetkov, Pushpendre Rastogi et al.

Lacking standardized extrinsic evaluation methods for vector representations of words, the NLP community has relied heavily on word similarity tasks as a proxy for intrinsic evaluation of word vectors. Word similarity evaluation, which correlates the distance between vectors and human judgments of semantic similarity is attractive, because it is computationally inexpensive and fast. In this paper we present several problems associated with the evaluation of word vectors on word similarity datasets, and summarize existing solutions. Our study suggests that the use of word similarity tasks for evaluation of word vectors is not sustainable and calls for further research on evaluation methods.

Shyam Upadhyay, Manaal Faruqui, Chris Dyer et al.

Despite interest in using cross-lingual knowledge to learn word embeddings for various tasks, a systematic comparison of the possible approaches is lacking in the literature. We perform an extensive evaluation of four popular approaches of inducing cross-lingual embeddings, each requiring a different form of supervision, on four typographically different language pairs. Our evaluation setup spans four different tasks, including intrinsic evaluation on mono-lingual and cross-lingual similarity, and extrinsic evaluation on downstream semantic and syntactic applications. We show that models which require expensive cross-lingual knowledge almost always perform better, but cheaply supervised models often prove competitive on certain tasks.

Manaal Faruqui, Yulia Tsvetkov, Graham Neubig et al.

Morphological inflection generation is the task of generating the inflected form of a given lemma corresponding to a particular linguistic transformation. We model the problem of inflection generation as a character sequence to sequence learning problem and present a variant of the neural encoder-decoder model for solving it. Our model is language independent and can be trained in both supervised and semi-supervised settings. We evaluate our system on seven datasets of morphologically rich languages and achieve either better or comparable results to existing state-of-the-art models of inflection generation.

Manaal Faruqui, Ryan McDonald, Radu Soricut

Morpho-syntactic lexicons provide information about the morphological and syntactic roles of words in a language. Such lexicons are not available for all languages and even when available, their coverage can be limited. We present a graph-based semi-supervised learning method that uses the morphological, syntactic and semantic relations between words to automatically construct wide coverage lexicons from small seed sets. Our method is language-independent, and we show that we can expand a 1000 word seed lexicon to more than 100 times its size with high quality for 11 languages. In addition, the automatically created lexicons provide features that improve performance in two downstream tasks: morphological tagging and dependency parsing.

Manaal Faruqui, Chris Dyer

Data-driven representation learning for words is a technique of central importance in NLP. While indisputably useful as a source of features in downstream tasks, such vectors tend to consist of uninterpretable components whose relationship to the categories of traditional lexical semantic theories is tenuous at best. We present a method for constructing interpretable word vectors from hand-crafted linguistic resources like WordNet, FrameNet etc. These vectors are binary (i.e, contain only 0 and 1) and are 99.9% sparse. We analyze their performance on state-of-the-art evaluation methods for distributional models of word vectors and find they are competitive to standard distributional approaches.

Manaal Faruqui, Yulia Tsvetkov, Dani Yogatama et al.

Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familiar, discrete classes (e.g., supersenses) and relations (e.g., synonymy and hypernymy). We propose methods that transform word vectors into sparse (and optionally binary) vectors. The resulting representations are more similar to the interpretable features typically used in NLP, though they are discovered automatically from raw corpora. Because the vectors are highly sparse, they are computationally easy to work with. Most importantly, we find that they outperform the original vectors on benchmark tasks.

Manaal Faruqui, Shankar Kumar

Open domain relation extraction systems identify relation and argument phrases in a sentence without relying on any underlying schema. However, current state-of-the-art relation extraction systems are available only for English because of their heavy reliance on linguistic tools such as part-of-speech taggers and dependency parsers. We present a cross-lingual annotation projection method for language independent relation extraction. We evaluate our method on a manually annotated test set and present results on three typologically different languages. We release these manual annotations and extracted relations in 61 languages from Wikipedia.

Manaal Faruqui, Jesse Dodge, Sujay K. Jauhar et al.

Vector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons such as WordNet, FrameNet, and the Paraphrase Database. This paper proposes a method for refining vector space representations using relational information from semantic lexicons by encouraging linked words to have similar vector representations, and it makes no assumptions about how the input vectors were constructed. Evaluated on a battery of standard lexical semantic evaluation tasks in several languages, we obtain substantial improvements starting with a variety of word vector models. Our refinement method outperforms prior techniques for incorporating semantic lexicons into the word vector training algorithms.

Dani Yogatama, Manaal Faruqui, Chris Dyer et al.

We propose a new method for learning word representations using hierarchical regularization in sparse coding inspired by the linguistic study of word meanings. We show an efficient learning algorithm based on stochastic proximal methods that is significantly faster than previous approaches, making it possible to perform hierarchical sparse coding on a corpus of billions of word tokens. Experiments on various benchmark tasks---word similarity ranking, analogies, sentence completion, and sentiment analysis---demonstrate that the method outperforms or is competitive with state-of-the-art methods. Our word representations are available at \url{http://www.ark.cs.cmu.edu/dyogatam/wordvecs/}.

Manaal Faruqui

Named Entities (NEs) are often written with no orthographic changes across different languages that share a common alphabet. We show that this can be leveraged so as to improve named entity recognition (NER) by using unsupervised word clusters from secondary languages as features in state-of-the-art discriminative NER systems. We observe significant increases in performance, finding that person and location identification is particularly improved, and that phylogenetically close languages provide more valuable features than more distant languages.

Nathan Schneider, Brendan O'Connor, Naomi Saphra et al.

We introduce a framework for lightweight dependency syntax annotation. Our formalism builds upon the typical representation for unlabeled dependencies, permitting a simple notation and annotation workflow. Moreover, the formalism encourages annotators to underspecify parts of the syntax if doing so would streamline the annotation process. We demonstrate the efficacy of this annotation on three languages and develop algorithms to evaluate and compare underspecified annotations.