arXiv subjects

Mihai Surdeanu

Publications and source records attributed to Mihai Surdeanu.

70 records · Page 4Linked to original sources

arXiv2020

The Language of Food during the Pandemic: Hints about the Dietary Effects of Covid-19

We study the language of food on Twitter during the pandemic lockdown in the United States, focusing on the two month period of March 15 to May 15, 2020. Specifically, we analyze over770,000 tweets published during the lockdown and the equivalent period in the five previous years and highlight several worrying trends. First, we observe that during the lockdown there was a notable shift from mentions of healthy foods to unhealthy foods. Second, we show an increased pointwise mutual information of depression hashtags with food-related tweets posted during the lockdown and an increased association between depression hashtags and unhealthy foods, tobacco, and alcohol during the lockdown.

cs.CL↗

arXiv2020

Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering

Evidence retrieval is a key component of explainable question answering (QA). We argue that, despite recent progress, transformer network-based approaches such as universal sentence encoder (USE-QA) do not always outperform traditional information retrieval (IR) methods such as BM25 for evidence retrieval for QA. We introduce a lexical probing task that validates this observation: we demonstrate that neural IR methods have the capacity to capture lexical differences between questions and answers, but miss obvious lexical overlap signal. Learning from this probing analysis, we introduce a hybrid approach for evidence retrieval that combines the advantages of both IR directions. Our approach uses a routing classifier that learns when to direct incoming questions to BM25 vs. USE-QA for evidence retrieval using very simple statistics, which can be efficiently extracted from the top candidate evidence sentences produced by a BM25 model. We demonstrate that this hybrid evidence retrieval generally performs better than either individual retrieval strategy on three QA datasets: OpenBookQA, ReQA SQuAD, and ReQA NQ. Furthermore, we show that the proposed routing strategy is considerably faster than neural methods, with a runtime that is up to 5 times faster than USE-QA.

cs.IR↗

arXiv2020

Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.

cs.CL↗

arXiv2020

Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering

We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. This unsupervised sentence selection method can be coupled with any supervised QA approach. We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2's Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC). We obtain new state-of-the-art performance on both datasets among approaches that do not use external resources for training the QA system: 56.82% F1 on ARC (41.24% on Challenge and 64.49% on Easy) and 26.1% EM0 on MultiRC. Our justification sentences have higher quality than the justifications selected by a strong information retrieval baseline, e.g., by 5.4% F1 in MultiRC. We also show that our unsupervised selection of justification sentences is more stable across domains than a state-of-the-art supervised sentence selection method.

cs.CL↗

arXiv2020

On the Importance of Delexicalization for Fact Verification

In this work we aim to understand and estimate the importance that a neural network assigns to various aspects of the data while learning and making predictions. Here we focus on the recognizing textual entailment (RTE) task and its application to fact verification. In this context, the contributions of this work are as follows. We investigate the attention weights a state of the art RTE method assigns to input tokens in the RTE component of fact verification systems, and confirm that most of the weight is assigned to POS tags of nouns (e.g., NN, NNP etc.) or their phrases. To verify that these lexicalized models transfer poorly, we implement a domain transfer experiment where a RTE component is trained on the FEVER data, and tested on the Fake News Challenge (FNC) dataset. As expected, even though this method achieves high accuracy when evaluated in the same domain, the performance in the target domain is poor, marginally above chance.To mitigate this dependence on lexicalized information, we experiment with several strategies for masking out names by replacing them with their semantic category, coupled with a unique identifier to mark that the same or new entities are referenced between claim and evidence. The results show that, while the performance on the FEVER dataset remains at par with that of the model trained on lexicalized data, it improves significantly when tested in the FNC dataset. Thus our experiments demonstrate that our strategy is successful in mitigating the dependency on lexical information.

cs.LG↗

arXiv2018

Sanity Check: A Strong Alignment and Information Retrieval Baseline for Question Answering

While increasingly complex approaches to question answering (QA) have been proposed, the true gain of these systems, particularly with respect to their expensive training requirements, can be inflated when they are not compared to adequate baselines. Here we propose an unsupervised, simple, and fast alignment and information retrieval baseline that incorporates two novel contributions: a \textit{one-to-many alignment} between query and document terms and \textit{negative alignment} as a proxy for discriminative information. Our approach not only outperforms all conventional baselines as well as many supervised recurrent neural networks, but also approaches the state of the art for supervised systems on three QA datasets. With only three hyperparameters, we achieve 47\% P@1 on an 8th grade Science QA dataset, 32.9\% P@1 on a Yahoo! answers QA dataset and 64\% MAP on WikiQA. We also achieve 26.56\% and 58.36\% on ARC challenge and easy dataset respectively. In addition to including the additional ARC results in this version of the paper, for the ARC easy set only we also experimented with one additional parameter -- number of justifications retrieved.

cs.IR↗

arXiv2018

Lightly-supervised Representation Learning with Global Interpretability

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning. Our algorithm iteratively learns custom embeddings for both the multi-word entities to be extracted and the patterns that match them from a few example entities per category. We demonstrate that this representation-based approach outperforms three other state-of-the-art bootstrapping approaches on two datasets: CoNLL-2003 and OntoNotes. Additionally, using these embeddings, our approach outputs a globally-interpretable model consisting of a decision list, by ranking patterns based on their proximity to the average entity embedding in a given class. We show that this interpretable model performs close to our complete bootstrapping model, proving that representation learning can be used to produce interpretable models with small loss in performance.

cs.CL↗

arXiv2018

Text Annotation Graphs: Annotating Complex Natural Language Phenomena

This paper introduces a new web-based software tool for annotating text, Text Annotation Graphs, or TAG. It provides functionality for representing complex relationships between words and word phrases that are not available in other software tools, including the ability to define and visualize relationships between the relationships themselves (semantic hypergraphs). Additionally, we include an approach to representing text annotations in which annotation subgraphs, or semantic summaries, are used to show relationships outside of the sequential context of the text itself. Users can use these subgraphs to quickly find similar structures within the current document or external annotated documents. Initially, TAG was developed to support information extraction tasks on a large database of biomedical articles. However, our software is flexible enough to support a wide range of annotation tasks for any domain. Examples are provided that showcase TAG's capabilities on morphological parsing and event extraction tasks. The TAG software is available at: https://github.com/ CreativeCodingLab/TextAnnotationGraphs.

cs.CL↗

arXiv2017

Learning what to read: Focused machine reading

Recent efforts in bioinformatics have achieved tremendous progress in the machine reading of biomedical literature, and the assembly of the extracted biochemical interactions into large-scale models such as protein signaling pathways. However, batch machine reading of literature at today's scale (PubMed alone indexes over 1 million papers per year) is unfeasible due to both cost and processing overhead. In this work, we introduce a focused reading approach to guide the machine reading of biomedical literature towards what literature should be read to answer a biomedical query as efficiently as possible. We introduce a family of algorithms for focused reading, including an intuitive, strong baseline, and a second approach which uses a reinforcement learning (RL) framework that learns when to explore (widen the search) or exploit (narrow it). We demonstrate that the RL approach is capable of answering more queries than the baseline, while being more efficient, i.e., reading fewer documents.

cs.AI↗

arXiv2016

Creating Causal Embeddings for Question Answering with Minimal Supervision

A common model for question answering (QA) is that a good answer is one that is closely related to the question, where relatedness is often determined using general-purpose lexical models such as word embeddings. We argue that a better approach is to look for answers that are related to the question in a relevant way, according to the information need of the question, which may be determined through task-specific embeddings. With causality as a use case, we implement this insight in three steps. First, we generate causal embeddings cost-effectively by bootstrapping cause-effect pairs extracted from free text using a small set of seed patterns. Second, we train dedicated embeddings over this data, by using task-specific contexts, i.e., the context of a cause is its effect. Finally, we extend a state-of-the-art reranking approach for QA to incorporate these causal embeddings. We evaluate the causal embedding models both directly with a casual implication task, and indirectly, in a downstream causal QA task using data from Yahoo! Answers. We show that explicitly modeling causality improves performance in both tasks. In the QA task our best model achieves 37.3% P@1, significantly outperforming a strong baseline by 7.7% (relative).

cs.CL↗

arXiv2016

Sieve-based Coreference Resolution in the Biomedical Domain

We describe challenges and advantages unique to coreference resolution in the biomedical domain, and a sieve-based architecture that leverages domain knowledge for both entity and event coreference resolution. Domain-general coreference resolution algorithms perform poorly on biomedical documents, because the cues they rely on such as gender are largely absent in this domain, and because they do not encode domain-specific knowledge such as the number and type of participants required in chemical reactions. Moreover, it is difficult to directly encode this knowledge into most coreference resolution algorithms because they are not rule-based. Our rule-based architecture uses sequentially applied hand-designed "sieves", with the output of each sieve informing and constraining subsequent sieves. This architecture provides a 3.2% increase in throughput to our Reach event extraction system with precision parallel to that of the stricter system that relies solely on syntactic patterns for extraction.

cs.CL↗

arXiv2016

SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction

We propose an approach for biomedical information extraction that marries the advantages of machine learning models, e.g., learning directly from data, with the benefits of rule-based approaches, e.g., interpretability. Our approach starts by training a feature-based statistical model, then converts this model to a rule-based variant by converting its features to rules, and "snapping to grid" the feature weights to discrete votes. In doing so, our proposal takes advantage of the large body of work in machine learning, but it produces an interpretable model, which can be directly edited by experts. We evaluate our approach on the BioNLP 2009 event extraction task. Our results show that there is a small performance penalty when converting the statistical model to rules, but the gain in interpretability compensates for that: with minimal effort, human experts improve this model to have similar performance to the statistical model that served as starting point.

cs.CL↗

arXiv2016

This before That: Causal Precedence in the Biomedical Domain

Causal precedence between biochemical interactions is crucial in the biomedical domain, because it transforms collections of individual interactions, e.g., bindings and phosphorylations, into the causal mechanisms needed to inform meaningful search and inference. Here, we analyze causal precedence in the biomedical domain as distinct from open-domain, temporal precedence. First, we describe a novel, hand-annotated text corpus of causal precedence in the biomedical domain. Second, we use this corpus to investigate a battery of models of precedence, covering rule-based, feature-based, and latent representation models. The highest-performing individual model achieved a micro F1 of 43 points, approaching the best performers on the simpler temporal-only precedence tasks. Feature-based and latent representation models each outperform the rule-based models, but their performance is complementary to one another. We apply a sieve-based architecture to capitalize on this lack of overlap, achieving a micro F1 score of 46 points.

cs.CL↗

arXiv2016

Towards using social media to identify individuals at risk for preventable chronic illness

We describe a strategy for the acquisition of training data necessary to build a social-media-driven early detection system for individuals at risk for (preventable) type 2 diabetes mellitus (T2DM). The strategy uses a game-like quiz with data and questions acquired semi-automatically from Twitter. The questions are designed to inspire participant engagement and collect relevant data to train a public-health model applied to individuals. Prior systems designed to use social media such as Twitter to predict obesity (a risk factor for T2DM) operate on entire communities such as states, counties, or cities, based on statistics gathered by government agencies. Because there is considerable variation among individuals within these groups, training data on the individual level would be more effective, but this data is difficult to acquire. The approach proposed here aims to address this issue. Our strategy has two steps. First, we trained a random forest classifier on data gathered from (public) Twitter statuses and state-level statistics with state-of-the-art accuracy. We then converted this classifier into a 20-questions-style quiz and made it available online. In doing so, we achieved high engagement with individuals that took the quiz, while also building a training set of voluntarily supplied individual-level data for future classification.

cs.CL↗

arXiv2015

Description of the Odin Event Extraction Framework and Rule Language

This document describes the Odin framework, which is a domain-independent platform for developing rule-based event extraction models. Odin aims to be powerful (the rule language allows the modeling of complex syntactic structures) and robust (to recover from syntactic parsing errors, syntactic patterns can be freely mixed with surface, token-based patterns), while remaining simple (some domain grammars can be up and running in minutes), and fast (Odin processes over 100 sentences/second in a real-world domain with over 200 rules). Here we include a thorough definition of the Odin rule language, together with a description of the Odin API in the Scala language, which allows one to apply these rules to arbitrary texts.

cs.CL↗

arXiv2014

Analyzing the Language of Food on Social Media

We investigate the predictive power behind the language of food on social media. We collect a corpus of over three million food-related posts from Twitter and demonstrate that many latent population characteristics can be directly predicted from this data: overweight rate, diabetes rate, political leaning, and home geographical location of authors. For all tasks, our language-based models significantly outperform the majority-class baselines. Performance is further improved with more complex natural language processing, such as topic modeling. We analyze which textual features have most predictive power for these datasets, providing insight into the connections between the language of food, geographic locale, and community characteristics. Lastly, we design and implement an online system for real-time query and visualization of the dataset. Visualization tools, such as geo-referenced heatmaps, semantics-preserving wordclouds and temporal histograms, allow us to discover more complex, global patterns mirrored in the language of food.

cs.CL↗