Riyaz Ahmad Bhat

Avirup Sil, Jaydeep Sen, Bhavani Iyer et al. · ibm-research

The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets with leaderboards, and novel algorithms for key components such as retrievers and readers. In this paper, we introduce PRIMEQA: a one-stop and open-source QA repository with an aim to democratize QA re-search and facilitate easy replication of state-of-the-art (SOTA) QA methods. PRIMEQA supports core QA functionalities like retrieval and reading comprehension as well as auxiliary capabilities such as question generation.It has been designed as an end-to-end toolkit for various use cases: building front-end applications, replicating SOTA methods on pub-lic benchmarks, and expanding pre-existing methods. PRIMEQA is available at : https://github.com/primeqa.

Rudra Murthy, Riyaz Bhat, Chulaka Gunasekara et al. · ibm-research

In this paper we explore the task of modeling semi-structured object sequences; in particular, we focus our attention on the problem of developing a structure-aware input representation for such sequences. Examples of such data include user activity on websites, machine logs, and many others. This type of data is often represented as a sequence of sets of key-value pairs over time and can present modeling challenges due to an ever-increasing sequence length. We propose a two-part approach, which first considers each key independently and encodes a representation of its values over time; we then self-attend over these value-aware key representations to accomplish a downstream task. This allows us to operate on longer object sequences than existing methods. We introduce a novel shared-attention-head architecture between the two modules and present an innovative training schedule that interleaves the training of both modules with shared weights for some attention heads. Our experiments on multiple prediction tasks using real-world data demonstrate that our approach outperforms a unified network with hierarchical encoding, as well as other methods including a record-centric representation and a flattened representation of the sequence.

Parul Awasthy, Aashka Trivedi, Yulong Li et al. · ibm-research

We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\% over leading competitors while maintaining superior accuracy. Our release encompasses both bi-encoder and cross-encoder architectures, featuring a highly effective 22-layer retriever model and its efficient 12-layer counterpart, alongside a high-quality reranker model, all trained exclusively on enterprise-appropriate data with comprehensive governance oversight. The models demonstrate exceptional versatility across standard benchmarks, IBM-developed evaluation suites, and real-world enterprise use cases, establishing new performance standards for open-source embedding models. In an era where retrieval speed and accuracy are paramount for competitive advantage, the Granite R2 models deliver a compelling combination of cutting-edge performance, enterprise-ready licensing, and transparent data provenance that organizations require for mission-critical deployments. All models are publicly available under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, enabling unrestricted research and commercial use.

Mayank Mishra, Prince Kumar, Riyaz Bhat et al.

Prompting with natural language instructions has recently emerged as a popular method of harnessing the capabilities of large language models. Given the inherent ambiguity present in natural language, it is intuitive to consider the possible advantages of prompting with less ambiguous prompt styles, such as the use of pseudo-code. In this paper we explore if prompting via pseudo-code instructions helps improve the performance of pre-trained language models. We manually create a dataset of pseudo-code prompts for 132 different tasks spanning classification, QA and generative language tasks, sourced from the Super-NaturalInstructions dataset. Using these prompts along with their counterparts in natural language, we study their performance on two LLM families - BLOOM and CodeGen. Our experiments show that using pseudo-code instructions leads to better results, with an average increase (absolute) of 7-16 points in F1 scores for classification tasks and an improvement (relative) of 12-38% in aggregate ROUGE-L scores across all tasks. We include detailed ablation studies which indicate that code comments, docstrings, and the structural clues encoded in pseudo-code all contribute towards the improvement in performance. To the best of our knowledge our work is the first to demonstrate how pseudo-code prompts can be helpful in improving the performance of pre-trained LMs.

Vivek Gupta, Riyaz A. Bhat, Atreya Ghosal et al.

Neural models command state-of-the-art performance across NLP tasks, including ones involving "reasoning". Models claiming to reason about the evidence presented to them should attend to the correct parts of the input avoiding spurious patterns therein, be self-consistent in their predictions across inputs, and be immune to biases derived from their pre-training in a nuanced, context-sensitive fashion. {\em Do the prevalent *BERT-family of models do so?} In this paper, we study this question using the problem of reasoning on tabular data. Tabular inputs are especially well-suited for the study -- they admit systematic probes targeting the properties listed above. Our experiments demonstrate that a RoBERTa-based model, representative of the current state-of-the-art, fails at reasoning on the following counts: it (a) ignores relevant parts of the evidence, (b) is over-sensitive to annotation artifacts, and (c) relies on the knowledge encoded in the pre-trained language model rather than the evidence presented in its tabular inputs. Finally, through inoculation experiments, we show that fine-tuning the model on perturbed data does not help it overcome the above challenges.

Riyaz Ahmad Bhat, Irshad Ahmad Bhat, Dipti Misra Sharma

We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate the sampling bias by generating all theoretically possible alternative word orders of a clause from the existing (kernel) structures in the treebank. Training our parser on canonical and transformed structures improves performance on conversational data by around 9% LAS over the baseline newswire parser.

Irshad Ahmad Bhat, Riyaz Ahmad Bhat, Manish Shrivastava et al.

Code-switching is a phenomenon of mixing grammatical structures of two or more languages under varied social constraints. The code-switching data differ so radically from the benchmark corpora used in NLP community that the application of standard technologies to these data degrades their performance sharply. Unlike standard corpora, these data often need to go through additional processes such as language identification, normalization and/or back-transliteration for their efficient processing. In this paper, we investigate these indispensable processes and other problems associated with syntactic parsing of code-switching data and propose methods to mitigate their effects. In particular, we study dependency parsing of code-switching data of Hindi and English multilingual speakers from Twitter. We present a treebank of Hindi-English code-switching tweets under Universal Dependencies scheme and propose a neural stacking model for parsing that efficiently leverages part-of-speech tag and syntactic tree annotations in the code-switching treebank and the preexisting Hindi and English treebanks. We also present normalization and back-transliteration models with a decoding process tailored for code-switching data. Results show that our neural stacking parser is 1.5% LAS points better than the augmented parsing model and our decoding process improves results by 3.8% LAS points over the first-best normalization and/or back-transliteration.

Irshad Ahmad Bhat, Riyaz Ahmad Bhat, Manish Shrivastava et al.

In this paper, we propose efficient and less resource-intensive strategies for parsing of code-mixed data. These strategies are not constrained by in-domain annotations, rather they leverage pre-existing monolingual annotated resources for training. We show that these methods can produce significantly better results as compared to an informed baseline. Besides, we also present a data set of 450 Hindi and English code-mixed tweets of Hindi multilingual speakers for evaluation. The data set is manually annotated with Universal Dependencies.