Mausam


2021

pdf bib
Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
Dinesh Raghu | Atishya Jain | Mausam | Sachindra Joshi
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

2020

pdf bib
Why and when should you pool? Analyzing Pooling in Recurrent Architectures
Pratyush Maini | Keshav Kolluru | Danish Pruthi | Mausam
Findings of the Association for Computational Linguistics: EMNLP 2020

Pooling-based recurrent neural architectures consistently outperform their counterparts without pooling on sequence classification tasks. However, the reasons for their enhanced performance are largely unexamined. In this work, we examine three commonly used pooling techniques (mean-pooling, max-pooling, and attention, and propose *max-attention*, a novel variant that captures interactions among predictive tokens in a sentence. Using novel experiments, we demonstrate that pooling architectures substantially differ from their non-pooling equivalents in their learning ability and positional biases: (i) pooling facilitates better gradient flow than BiLSTMs in initial training epochs, and (ii) BiLSTMs are biased towards tokens at the beginning and end of the input, whereas pooling alleviates this bias. Consequently, we find that pooling yields large gains in low resource scenarios, and instances when salient words lie towards the middle of the input. Across several text classification tasks, we find max-attention to frequently outperform other pooling techniques.

pdf bib
IMoJIE: Iterative Memory-Based Joint Open Information Extraction
Keshav Kolluru | Samarth Aggarwal | Vipul Rathore | Mausam | Soumen Chakrabarti
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task. Our work builds upon CopyAttention, a sequence generation OpenIE model (Cui et. al. 18). Our analysis reveals that CopyAttention produces a constant number of extractions per sentence, and its extracted tuples often express redundant information. We present IMoJIE, an extension to CopyAttention, which produces the next extraction conditioned on all previously extracted tuples. This approach overcomes both shortcomings of CopyAttention, resulting in a variable number of diverse extractions per sentence. We train IMoJIE on training data bootstrapped from extractions of several non-neural systems, which have been automatically filtered to reduce redundancy and noise. IMoJIE outperforms CopyAttention by about 18 F1 pts, and a BERT-based strong baseline by 2 F1 pts, establishing a new state of the art for the task.

pdf bib
Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols
Prachi Jain | Sushant Rathi | Mausam | Soumen Chakrabarti
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Research on temporal knowledge bases, which associate a relational fact (s,r,o) with a validity time period (or time instant), is in its early days. Our work considers predicting missing entities (link prediction) and missing time intervals (time prediction) as joint Temporal Knowledge Base Completion (TKBC) tasks, and presents TIMEPLEX, a novel TKBC method, in which entities, relations and, time are all embedded in a uniform, compatible space. TIMEPLEX exploits the recurrent nature of some facts/events and temporal interactions between pairs of relations, yielding state-of-the-art results on both prediction tasks. We also find that existing TKBC models heavily overestimate link prediction performance due to imperfect evaluation mechanisms. In response, we propose improved TKBC evaluation protocols for both link and time prediction tasks, dealing with subtle issues that arise from the partial overlap of time intervals in gold instances and system predictions.

pdf bib
OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction
Keshav Kolluru | Vaibhav Adlakha | Samarth Aggarwal | Mausam | Soumen Chakrabarti
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

A recent state-of-the-art neural open information extraction (OpenIE) system generates extractions iteratively, requiring repeated encoding of partial outputs. This comes at a significant computational cost. On the other hand,sequence labeling approaches for OpenIE are much faster, but worse in extraction quality. In this paper, we bridge this trade-off by presenting an iterative labeling-based system that establishes a new state of the art for OpenIE, while extracting 10x faster. This is achieved through a novel Iterative Grid Labeling (IGL) architecture, which treats OpenIE as a 2-D grid labeling task. We improve its performance further by applying coverage (soft) constraints on the grid at training time. Moreover, on observing that the best OpenIE systems falter at handling coordination structures, our OpenIE system also incorporates a new coordination analyzer built with the same IGL architecture. This IGL based coordination analyzer helps our OpenIE system handle complicated coordination structures, while also establishing a new state of the art on the task of coordination analysis, with a 12.3 pts improvement in F1 over previous analyzers. Our OpenIE system - OpenIE6 - beats the previous systems by as much as 4 pts in F1, while being much faster.

pdf bib
A Simple Yet Strong Pipeline for HotpotQA
Dirk Groeneveld | Tushar Khot | Mausam | Ashish Sabharwal
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition. However, does their strong performance on popular multi-hop datasets really justify this added design complexity? Our results suggest that the answer may be no, because even our simple pipeline based on BERT, named , performs surprisingly well. Specifically, on HotpotQA, Quark outperforms these models on both question answering and support identification (and achieves performance very close to a RoBERTa model). Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences independently of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. The strong performance of Quark resurfaces the importance of carefully exploring simple model designs before using popular benchmarks to justify the value of complex techniques.

2019

pdf bib
Disentangling Language and Knowledge in Task-Oriented Dialogs
Dinesh Raghu | Nikhil Gupta | Mausam
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)

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response’s language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNeT outperforms state-of-the-art models, with considerable improvements (>10%) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNeT to be robust to KB modifications.

2018

pdf bib
Open Information Extraction from Conjunctive Sentences
Swarnadeep Saha | Mausam
Proceedings of the 27th International Conference on Computational Linguistics

We develop CALM, a coordination analyzer that improves upon the conjuncts identified from dependency parses. It uses a language model based scoring and several linguistic constraints to search over hierarchical conjunct boundaries (for nested coordination). By splitting a conjunctive sentence around these conjuncts, CALM outputs several simple sentences. We demonstrate the value of our coordination analyzer in the end task of Open Information Extraction (Open IE). State-of-the-art Open IE systems lose substantial yield due to ineffective processing of conjunctive sentences. Our Open IE system, CALMIE, performs extraction over the simple sentences identified by CALM to obtain up to 1.8x yield with a moderate increase in precision compared to extractions from original sentences.

pdf bib
Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision
Prachi Jain | Pankaj Kumar | Mausam | Soumen Chakrabarti
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

State-of-the-art knowledge base completion (KBC) models predict a score for every known or unknown fact via a latent factorization over entity and relation embeddings. We observe that when they fail, they often make entity predictions that are incompatible with the type required by the relation. In response, we enhance each base factorization with two type-compatibility terms between entity-relation pairs, and combine the signals in a novel manner. Without explicit supervision from a type catalog, our proposed modification obtains up to 7% MRR gains over base models, and new state-of-the-art results on several datasets. Further analysis reveals that our models better represent the latent types of entities and their embeddings also predict supervised types better than the embeddings fitted by baseline models.

2017

pdf bib
Bootstrapping for Numerical Open IE
Swarnadeep Saha | Harinder Pal | Mausam
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

We design and release BONIE, the first open numerical relation extractor, for extracting Open IE tuples where one of the arguments is a number or a quantity-unit phrase. BONIE uses bootstrapping to learn the specific dependency patterns that express numerical relations in a sentence. BONIE’s novelty lies in task-specific customizations, such as inferring implicit relations, which are clear due to context such as units (for e.g., ‘square kilometers’ suggests area, even if the word ‘area’ is missing in the sentence). BONIE obtains 1.5x yield and 15 point precision gain on numerical facts over a state-of-the-art Open IE system.

2016

pdf bib
Demonyms and Compound Relational Nouns in Nominal Open IE
Harinder Pal | Mausam
Proceedings of the 5th Workshop on Automated Knowledge Base Construction

pdf bib
Entity-balanced Gaussian pLSA for Automated Comparison
Danish Contractor | Parag Singla | Mausam
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Knowledge-Guided Linguistic Rewrites for Inference Rule Verification
Prachi Jain | Mausam
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2015

pdf bib
Open IE as an Intermediate Structure for Semantic Tasks
Gabriel Stanovsky | Ido Dagan | Mausam
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

2014

pdf bib
Hierarchical Summarization: Scaling Up Multi-Document Summarization
Janara Christensen | Stephen Soderland | Gagan Bansal | Mausam
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2013

pdf bib
Generating Coherent Event Schemas at Scale
Niranjan Balasubramanian | Stephen Soderland | Mausam | Oren Etzioni
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Towards Coherent Multi-Document Summarization
Janara Christensen | Mausam | Stephen Soderland | Oren Etzioni
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Modeling Missing Data in Distant Supervision for Information Extraction
Alan Ritter | Luke Zettlemoyer | Mausam | Oren Etzioni
Transactions of the Association for Computational Linguistics, Volume 1

Distant supervision algorithms learn information extraction models given only large readily available databases and text collections. Most previous work has used heuristics for generating labeled data, for example assuming that facts not contained in the database are not mentioned in the text, and facts in the database must be mentioned at least once. In this paper, we propose a new latent-variable approach that models missing data. This provides a natural way to incorporate side information, for instance modeling the intuition that text will often mention rare entities which are likely to be missing in the database. Despite the added complexity introduced by reasoning about missing data, we demonstrate that a carefully designed local search approach to inference is very accurate and scales to large datasets. Experiments demonstrate improved performance for binary and unary relation extraction when compared to learning with heuristic labels, including on average a 27% increase in area under the precision recall curve in the binary case.

2012

pdf bib
Open Language Learning for Information Extraction
Mausam | Michael Schmitz | Stephen Soderland | Robert Bart | Oren Etzioni
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

pdf bib
No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities
Thomas Lin | Mausam | Oren Etzioni
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

pdf bib
Entity Linking at Web Scale
Thomas Lin | Mausam | Oren Etzioni
Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX)

pdf bib
Rel-grams: A Probabilistic Model of Relations in Text
Niranjan Balasubramanian | Stephen Soderland | Mausam | Oren Etzioni
Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX)

2011

pdf bib
Named Entity Recognition in Tweets: An Experimental Study
Alan Ritter | Sam Clark | Mausam | Oren Etzioni
Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing

2010

pdf bib
Semantic Role Labeling for Open Information Extraction
Janara Christensen | Mausam | Stephen Soderland | Oren Etzioni
Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading

pdf bib
Machine Reading at the University of Washington
Hoifung Poon | Janara Christensen | Pedro Domingos | Oren Etzioni | Raphael Hoffmann | Chloe Kiddon | Thomas Lin | Xiao Ling | Mausam | Alan Ritter | Stefan Schoenmackers | Stephen Soderland | Dan Weld | Fei Wu | Congle Zhang
Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading

pdf bib
A Latent Dirichlet Allocation Method for Selectional Preferences
Alan Ritter | Mausam | Oren Etzioni
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Identifying Functional Relations in Web Text
Thomas Lin | Mausam | Oren Etzioni
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

2009

pdf bib
Compiling a Massive, Multilingual Dictionary via Probabilistic Inference
Mausam | Stephen Soderland | Oren Etzioni | Daniel Weld | Michael Skinner | Jeff Bilmes
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
A Rose is a Roos is a Ruusu: Querying Translations for Web Image Search
Janara Christensen | Mausam | Oren Etzioni
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers