Mandar Joshi


Improving Passage Retrieval with Zero-Shot Question Generation
Devendra Sachan | Mike Lewis | Mandar Joshi | Armen Aghajanyan | Wen-tau Yih | Joelle Pineau | Luke Zettlemoyer
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new re-ranker to existing models with no further changes.


DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions
Weijia Shi | Mandar Joshi | Luke Zettlemoyer
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Short textual descriptions of entities provide summaries of their key attributes and have been shown to be useful sources of background knowledge for tasks such as entity linking and question answering. However, generating entity descriptions, especially for new and long-tail entities, can be challenging since relevant information is often scattered across multiple sources with varied content and style. We introduce DESCGEN: given mentions spread over multiple documents, the goal is to generate an entity summary description. DESCGEN consists of 37K entity descriptions from Wikipedia and Fandom, each paired with nine evidence documents on average. The documents were collected using a combination of entity linking and hyperlinks into the entity pages, which together provide high-quality distant supervision. Compared to other multi-document summarization tasks, our task is entity-centric, more abstractive, and covers a wide range of domains. We also propose a two-stage extract-then-generate baseline and show that there exists a large gap (19.9% in ROUGE-L) between state-of-art models and human performance, suggesting that the data will support significant future work.

FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary
Terra Blevins | Mandar Joshi | Luke Zettlemoyer
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Current models for Word Sense Disambiguation (WSD) struggle to disambiguate rare senses, despite reaching human performance on global WSD metrics. This stems from a lack of data for both modeling and evaluating rare senses in existing WSD datasets. In this paper, we introduce FEWS (Few-shot Examples of Word Senses), a new low-shot WSD dataset automatically extracted from example sentences in Wiktionary. FEWS has high sense coverage across different natural language domains and provides: (1) a large training set that covers many more senses than previous datasets and (2) a comprehensive evaluation set containing few- and zero-shot examples of a wide variety of senses. We establish baselines on FEWS with knowledge-based and neural WSD approaches and present transfer learning experiments demonstrating that models additionally trained with FEWS better capture rare senses in existing WSD datasets. Finally, we find humans outperform the best baseline models on FEWS, indicating that FEWS will support significant future work on low-shot WSD.

Realistic Evaluation Principles for Cross-document Coreference Resolution
Arie Cattan | Alon Eirew | Gabriel Stanovsky | Mandar Joshi | Ido Dagan
Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics

We point out that common evaluation practices for cross-document coreference resolution have been unrealistically permissive in their assumed settings, yielding inflated results. We propose addressing this issue via two evaluation methodology principles. First, as in other tasks, models should be evaluated on predicted mentions rather than on gold mentions. Doing this raises a subtle issue regarding singleton coreference clusters, which we address by decoupling the evaluation of mention detection from that of coreference linking. Second, we argue that models should not exploit the synthetic topic structure of the standard ECB+ dataset, forcing models to confront the lexical ambiguity challenge, as intended by the dataset creators. We demonstrate empirically the drastic impact of our more realistic evaluation principles on a competitive model, yielding a score which is 33 F1 lower compared to evaluating by prior lenient practices.

Cross-document Coreference Resolution over Predicted Mentions
Arie Cattan | Alon Eirew | Gabriel Stanovsky | Mandar Joshi | Ido Dagan
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


SpanBERT: Improving Pre-training by Representing and Predicting Spans
Mandar Joshi | Danqi Chen | Yinhan Liu | Daniel S. Weld | Luke Zettlemoyer | Omer Levy
Transactions of the Association for Computational Linguistics, Volume 8

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary representations to predict the entire content of the masked span, without relying on the individual token representations within it. SpanBERT consistently outperforms BERT and our better-tuned baselines, with substantial gains on span selection tasks such as question answering and coreference resolution. In particular, with the same training data and model size as BERTlarge, our single model obtains 94.6% and 88.7% F1 on SQuAD 1.1 and 2.0 respectively. We also achieve a new state of the art on the OntoNotes coreference resolution task (79.6% F1), strong performance on the TACRED relation extraction benchmark, and even gains on GLUE.1

An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
Bhargavi Paranjape | Mandar Joshi | John Thickstun | Hannaneh Hajishirzi | Luke Zettlemoyer
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Decisions of complex models for language understanding can be explained by limiting the inputs they are provided to a relevant subsequence of the original text — a rationale. Models that condition predictions on a concise rationale, while being more interpretable, tend to be less accurate than models that are able to use the entire context. In this paper, we show that it is possible to better manage the trade-off between concise explanations and high task accuracy by optimizing a bound on the Information Bottleneck (IB) objective. Our approach jointly learns an explainer that predicts sparse binary masks over input sentences without explicit supervision, and an end-task predictor that considers only the residual sentences. Using IB, we derive a learning objective that allows direct control of mask sparsity levels through a tunable sparse prior. Experiments on the ERASER benchmark demonstrate significant gains over previous work for both task performance and agreement with human rationales. Furthermore, we find that in the semi-supervised setting, a modest amount of gold rationales (25% of training examples with gold masks) can close the performance gap with a model that uses the full input.


BERT for Coreference Resolution: Baselines and Analysis
Mandar Joshi | Omer Levy | Luke Zettlemoyer | Daniel Weld
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We apply BERT to coreference resolution, achieving a new state of the art on the GAP (+11.5 F1) and OntoNotes (+3.9 F1) benchmarks. A qualitative analysis of model predictions indicates that, compared to ELMo and BERT-base, BERT-large is particularly better at distinguishing between related but distinct entities (e.g., President and CEO), but that there is still room for improvement in modeling document-level context, conversations, and mention paraphrasing. We will release all code and trained models upon publication.

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
Mandar Joshi | Eunsol Choi | Omer Levy | Daniel Weld | Luke Zettlemoyer
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Reasoning about implied relationships (e.g. paraphrastic, common sense, encyclopedic) between pairs of words is crucial for many cross-sentence inference problems. This paper proposes new methods for learning and using embeddings of word pairs that implicitly represent background knowledge about such relationships. Our pairwise embeddings are computed as a compositional function of each word’s representation, which is learned by maximizing the pointwise mutual information (PMI) with the contexts in which the the two words co-occur. We add these representations to the cross-sentence attention layer of existing inference models (e.g. BiDAF for QA, ESIM for NLI), instead of extending or replacing existing word embeddings. Experiments show a gain of 2.7% on the recently released SQuAD 2.0 and 1.3% on MultiNLI. Our representations also aid in better generalization with gains of around 6-7% on adversarial SQuAD datasets, and 8.8% on the adversarial entailment test set by Glockner et al. (2018).


TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Mandar Joshi | Eunsol Choi | Daniel Weld | Luke Zettlemoyer
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We present TriviaQA, a challenging reading comprehension dataset containing over 650K question-answer-evidence triples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts and independently gathered evidence documents, six per question on average, that provide high quality distant supervision for answering the questions. We show that, in comparison to other recently introduced large-scale datasets, TriviaQA (1) has relatively complex, compositional questions, (2) has considerable syntactic and lexical variability between questions and corresponding answer-evidence sentences, and (3) requires more cross sentence reasoning to find answers. We also present two baseline algorithms: a feature-based classifier and a state-of-the-art neural network, that performs well on SQuAD reading comprehension. Neither approach comes close to human performance (23% and 40% vs. 80%), suggesting that TriviaQA is a challenging testbed that is worth significant future study.


Knowledge Graph and Corpus Driven Segmentation and Answer Inference for Telegraphic Entity-seeking Queries
Mandar Joshi | Uma Sawant | Soumen Chakrabarti
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)