Arash Einolghozati

Man Luo, Shashank Jain, Anchit Gupta et al. · meta-ai

Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study "Is it possible to reduce the indexing memory of hybrid retrievers without sacrificing performance"? Driven by this question, we leverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost. LITE is jointly trained on contrastive learning and knowledge distillation from DrBoost. Then, we integrate BM25, a sparse retriever, with either LITE or DrBoost to form light hybrid retrievers. Our Hybrid-LITE retriever saves 13X memory while maintaining 98.0% performance of the hybrid retriever of BM25 and DPR. In addition, we study the generalization capacity of our light hybrid retrievers on out-of-domain dataset and a set of adversarial attacks datasets. Experiments showcase that light hybrid retrievers achieve better generalization performance than individual sparse and dense retrievers. Nevertheless, our analysis shows that there is a large room to improve the robustness of retrievers, suggesting a new research direction.

Asish Ghoshal, Arash Einolghozati, Ankit Arun et al. · berkeley, meta-ai

Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries. In this paper, we show that factual inconsistency can be caused by irrelevant parts of the input text, which act as confounders. To that end, we leverage information-theoretic measures of causal effects to quantify the amount of confounding and precisely quantify how they affect the summarization performance. Based on insights derived from our theoretical results, we design a simple multi-task model to control such confounding by leveraging human-annotated relevant sentences when available. Crucially, we give a principled characterization of data distributions where such confounding can be large thereby necessitating the use of human annotated relevant sentences to generate factual summaries. Our approach improves faithfulness scores by 20\% over strong baselines on AnswerSumm \citep{fabbri2021answersumm}, a conversation summarization dataset where lack of faithfulness is a significant issue due to the subjective nature of the task. Our best method achieves the highest faithfulness score while also achieving state-of-the-art results on standard metrics like ROUGE and METEOR. We corroborate these improvements through human evaluation.

Patrick Huber, Arash Einolghozati, Rylan Conway et al. · meta-ai

Distilling conversational skills into Small Language Models (SLMs) with approximately 1 billion parameters presents significant challenges. Firstly, SLMs have limited capacity in their model parameters to learn extensive knowledge compared to larger models. Secondly, high-quality conversational datasets are often scarce, small, and domain-specific. Addressing these challenges, we introduce a novel data distillation framework named CoDi (short for Conversational Distillation, pronounced "Cody"), allowing us to synthesize large-scale, assistant-style datasets in a steerable and diverse manner. Specifically, while our framework is task agnostic at its core, we explore and evaluate the potential of CoDi on the task of conversational grounded reasoning for question answering. This is a typical on-device scenario for specialist SLMs, allowing for open-domain model responses, without requiring the model to "memorize" world knowledge in its limited weights. Our evaluations show that SLMs trained with CoDi-synthesized data achieve performance comparable to models trained on human-annotated data in standard metrics. Additionally, when using our framework to generate larger datasets from web data, our models surpass larger, instruction-tuned models in zero-shot conversational grounded reasoning tasks.

Sahithya Ravi, Patrick Huber, Akshat Shrivastava et al. · meta-ai

The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing. Consequently, distillation through imitation of teacher responses has emerged as a popular technique to transfer knowledge from LLMs to more accessible, Small Language Models (SLMs). While this works well for simpler tasks, there is a substantial performance gap on tasks requiring intricate language comprehension and creativity, such as humor generation. We hypothesize that this gap may stem from the fact that creative tasks might be hard to learn by imitation alone and explore whether an approach, involving supplementary guidance from the teacher, could yield higher performance. To address this, we study the effect of assigning a dual role to the LLM - as a "teacher" generating data, as well as a "critic" evaluating the student's performance. Our experiments on humor generation reveal that the incorporation of feedback significantly narrows the performance gap between SLMs and their larger counterparts compared to merely relying on imitation. As a result, our research highlights the potential of using feedback as an additional dimension to data when transferring complex language abilities via distillation.

Haoran Li, Arash Einolghozati, Srinivasan Iyer et al.

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework for evidence-based text generation and apply it to document summarization. We present an explainable summarization system based on the Information Bottleneck principle that is jointly trained for extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans as explanations and then generates a summary using only the evidence. Using automatic and human evaluations, we show that explanations from our framework are more relevant than simple baselines, without substantially sacrificing the quality of the generated summary.

Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda et al.

Being able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales. In this work, we focus on Spanglish (Spanish+English) and release a dataset, CSTOP, containing 5800 CS utterances alongside their semantic parses. We examine the CS generalizability of various Cross-lingual (XL) models and exhibit the advantage of pre-trained XL language models when data for only one language is present. As such, we focus on improving the pre-trained models for the case when only English corpus alongside either zero or a few CS training instances are available. We propose two data augmentation methods for the zero-shot and the few-shot settings: fine-tune using translate-and-align and augment using a generation model followed by match-and-filter. Combining the few-shot setting with the above improvements decreases the initial 30-point accuracy gap between the zero-shot and the full-data settings by two thirds.

Arash Einolghozati, Anchit Gupta, Keith Diedrick et al.

We introduce a new task of rephrasing for a more natural virtual assistant. Currently, virtual assistants work in the paradigm of intent slot tagging and the slot values are directly passed as-is to the execution engine. However, this setup fails in some scenarios such as messaging when the query given by the user needs to be changed before repeating it or sending it to another user. For example, for queries like 'ask my wife if she can pick up the kids' or 'remind me to take my pills', we need to rephrase the content to 'can you pick up the kids' and 'take your pills' In this paper, we study the problem of rephrasing with messaging as a use case and release a dataset of 3000 pairs of original query and rephrased query. We show that BART, a pre-trained transformers-based masked language model with auto-regressive decoding, is a strong baseline for the task, and show improvements by adding a copy-pointer and copy loss to it. We analyze different tradeoffs of BART-based and LSTM-based seq2seq models, and propose a distilled LSTM-based seq2seq as the best practical model.

Varun Gangal, Abhinav Arora, Arash Einolghozati et al.

The task of identifying out-of-domain (OOD) input examples directly at test-time has seen renewed interest recently due to increased real world deployment of models. In this work, we focus on OOD detection for natural language sentence inputs to task-based dialog systems. Our findings are three-fold: First, we curate and release ROSTD (Real Out-of-Domain Sentences From Task-oriented Dialog) - a dataset of 4K OOD examples for the publicly available dataset from (Schuster et al. 2019). In contrast to existing settings which synthesize OOD examples by holding out a subset of classes, our examples were authored by annotators with apriori instructions to be out-of-domain with respect to the sentences in an existing dataset. Second, we explore likelihood ratio based approaches as an alternative to currently prevalent paradigms. Specifically, we reformulate and apply these approaches to natural language inputs. We find that they match or outperform the latter on all datasets, with larger improvements on non-artificial OOD benchmarks such as our dataset. Our ablations validate that specifically using likelihood ratios rather than plain likelihood is necessary to discriminate well between OOD and in-domain data. Third, we propose learning a generative classifier and computing a marginal likelihood (ratio) for OOD detection. This allows us to use a principled likelihood while at the same time exploiting training-time labels. We find that this approach outperforms both simple likelihood (ratio) based and other prior approaches. We are hitherto the first to investigate the use of generative classifiers for OOD detection at test-time.

Arash Einolghozati, Sonal Gupta, Mrinal Mohit et al.

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word tagging techniques respectively. Similar to adversarial attack problems with computer vision models discussed in existing literature, these intent-slot tagging models are often over-sensitive to small variations in input -- predicting different and often incorrect labels when small changes are made to a query, thus reducing their accuracy and reliability. However, evaluating a model's robustness to these changes is harder for language since words are discrete and an automated change (e.g. adding `noise') to a query sometimes changes the meaning and thus labels of a query. In this paper, we first describe how to create an adversarial test set to measure the robustness of these models. Furthermore, we introduce and adapt adversarial training methods as well as data augmentation using back-translation to mitigate these issues. Our experiments show that both techniques improve the robustness of the system substantially and can be combined to yield the best results.

Arash Einolghozati, Panupong Pasupat, Sonal Gupta et al.

Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results [Gupta et al 2018]. In this paper, we present three different improvements to the model: contextualized embeddings, ensembling, and pairwise re-ranking based on a language model. We taxonomize the errors possible for the hierarchical representation, such as wrong top intent, missing spans or split spans, and show that the three approaches correct different kinds of errors. The best model combines the three techniques and gives 6.4% better exact match accuracy than the state-of-the-art, with an error reduction of 33%, resulting in a new state-of-the-art result on the Task Oriented Parsing (TOP) dataset.

Colin Lockard, Xin Luna Dong, Arash Einolghozati et al.

The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high precision and recall only when manual annotations for each website are available. Although there have been efforts to learn extractors from automatically-generated labels, these methods are not sufficiently robust to succeed in settings with complex schemas and information-rich websites. In this paper we present a new method for automatic extraction from semi-structured websites based on distant supervision. We automatically generate training labels by aligning an existing knowledge base with a web page and leveraging the unique structural characteristics of semi-structured websites. We then train a classifier based on the potentially noisy and incomplete labels to predict new relation instances. Our method can compete with annotation-based techniques in the literature in terms of extraction quality. A large-scale experiment on over 400,000 pages from dozens of multi-lingual long-tail websites harvested 1.25 million facts at a precision of 90%.

Parminder Bhatia, Marsal Gavalda, Arash Einolghozati

While liking or upvoting a post on a mobile app is easy to do, replying with a written note is much more difficult, due to both the cognitive load of coming up with a meaningful response as well as the mechanics of entering the text. Here we present a novel textual reply generation model that goes beyond the current auto-reply and predictive text entry models by taking into account the content preferences of the user, the idiosyncrasies of their conversational style, and even the structure of their social graph. Specifically, we have developed two types of models for personalized user interactions: a content-based conversation model, which makes use of location together with user information, and a social-graph-based conversation model, which combines content-based conversation models with social graphs.

Erman Ayday, Arash Einolghozati, Faramarz Fekri

In this paper we introduce the first application of the Belief Propagation (BP) algorithm in the design of recommender systems. We formulate the recommendation problem as an inference problem and aim to compute the marginal probability distributions of the variables which represent the ratings to be predicted. However, computing these marginal probability functions is computationally prohibitive for large-scale systems. Therefore, we utilize the BP algorithm to efficiently compute these functions. Recommendations for each active user are then iteratively computed by probabilistic message passing. As opposed to the previous recommender algorithms, BPRS does not require solving the recommendation problem for all the users if it wishes to update the recommendations for only a single active. Further, BPRS computes the recommendations for each user with linear complexity and without requiring a training period. Via computer simulations (using the 100K MovieLens dataset), we verify that BPRS iteratively reduces the error in the predicted ratings of the users until it converges. Finally, we confirm that BPRS is comparable to the state of art methods such as Correlation-based neighborhood model (CorNgbr) and Singular Value Decomposition (SVD) in terms of rating and precision accuracy. Therefore, we believe that the BP-based recommendation algorithm is a new promising approach which offers a significant advantage on scalability while providing competitive accuracy for the recommender systems.