Marina Danilevsky


2024

pdf bib
Evaluating Robustness of Open Dialogue Summarization Models in the Presence of Naturally Occurring Variations
Ankita Gupta | Chulaka Gunasekara | Hui Wan | Jatin Ganhotra | Sachindra Joshi | Marina Danilevsky
Proceedings of the 6th Workshop on NLP for Conversational AI (NLP4ConvAI 2024)

Dialogue summarization involves summarizing long conversations while preserving the most salient information. Real-life dialogues often involve naturally occurring variations (e.g., repetitions, hesitations). In this study, we systematically investigate the impact of such variations on state-of-the-art open dialogue summarization models whose details are publicly known (e.g., architectures, weights, and training corpora). To simulate real-life variations, we introduce two types of perturbations: utterance-level perturbations that modify individual utterances with errors and language variations, and dialogue-level perturbations that add non-informative exchanges (e.g., repetitions, greetings). We perform our analysis along three dimensions of robustness: consistency, saliency, and faithfulness, which aim to capture different aspects of performance of a summarization model. We find that both fine-tuned and instruction-tuned models are affected by input variations, with the latter being more susceptible, particularly to dialogue-level perturbations. We also validate our findings via human evaluation. Finally, we investigate whether the robustness of fine-tuned models can be improved by training them with a fraction of perturbed data. We find that this approach does not yield consistent performance gains, warranting further research. Overall, our work highlights robustness challenges in current open encoder-decoder summarization models and provides insights for future research.

2023

pdf bib
PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation
Ishan Jindal | Alexandre Rademaker | Khoi-Nguyen Tran | Huaiyu Zhu | Hiroshi Kanayama | Marina Danilevsky | Yunyao Li
Findings of the Association for Computational Linguistics: EACL 2023

Semantic role labeling (SRL) identifies the predicate-argument structure in a sentence. This task is usually accomplished in four steps: predicate identification, predicate sense disambiguation, argument identification, and argument classification. Errors introduced at one step propagate to later steps. Unfortunately, the existing SRL evaluation scripts do not consider the full effect of this error propagation aspect. They either evaluate arguments independent of predicate sense (CoNLL09) or do not evaluate predicate sense at all (CoNLL05), yielding an inaccurate SRL model performance on the argument classification task. In this paper, we address key practical issues with existing evaluation scripts and propose a more strict SRL evaluation metric PriMeSRL. We observe that by employing PriMeSRL, the quality evaluation of all SoTA SRL models drops significantly, and their relative rankings also change. We also show that PriMeSRLsuccessfully penalizes actual failures in SoTA SRL models.

pdf bib
Semi-Structured Object Sequence Encoders
Rudra Murthy | Riyaz Bhat | Chulaka Gunasekara | Siva Patel | Hui Wan | Tejas Dhamecha | Danish Contractor | Marina Danilevsky
Findings of the Association for Computational Linguistics: EMNLP 2023

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.

2022

pdf bib
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Eyal Shnarch | Alon Halfon | Ariel Gera | Marina Danilevsky | Yannis Katsis | Leshem Choshen | Martin Santillan Cooper | Dina Epelboim | Zheng Zhang | Dakuo Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Label Sleuth is an open source platform for building text classifiers which does not require coding skills nor machine learning knowledge.- Project website: [https://www.label-sleuth.org/](https://www.label-sleuth.org/)- Link to screencast video: [https://vimeo.com/735675461](https://vimeo.com/735675461)### AbstractText classification can be useful in many real-world scenarios, saving a lot of time for end users. However, building a classifier generally requires coding skills and ML knowledge, which poses a significant barrier for many potential users. To lift this barrier we introduce *Label Sleuth*, a free open source system for labeling and creating text classifiers. This system is unique for: - being a no-code system, making NLP accessible for non-experts. - guiding its users throughout the entire labeling process until they obtain their desired classifier, making the process efficient - from cold start to a classifier in a few hours. - being open for configuration and extension by developers. By open sourcing Label Sleuth we hope to build a community of users and developers that will widen the utilization of NLP models.

pdf bib
Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming
Ayush Maheshwari | Krishnateja Killamsetty | Ganesh Ramakrishnan | Rishabh Iyer | Marina Danilevsky | Lucian Popa
Findings of the Association for Computational Linguistics: ACL 2022

A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time-consuming to obtain. Although a small amount of labeled data cannot be used to train a model, it can be used effectively for the generation of humaninterpretable labeling functions (LFs). These LFs, in turn, have been used to generate a large amount of additional noisy labeled data in a paradigm that is now commonly referred to as data programming. Previous methods of generating LFs do not attempt to use the given labeled data further to train a model, thus missing opportunities for improving performance. Additionally, since the LFs are generated automatically, they are likely to be noisy, and naively aggregating these LFs can lead to suboptimal results. In this work, we propose an LF-based bi-level optimization framework WISDOM to solve these two critical limitations. WISDOM learns a joint model on the (same) labeled dataset used for LF induction along with any unlabeled data in a semi-supervised manner, and more critically, reweighs each LF according to its goodness, influencing its contribution to the semi-supervised loss using a robust bi-level optimization algorithm. We show that WISDOM significantly outperforms prior approaches on several text classification datasets.

2021

pdf bib
SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)
Nancy X. R. Wang | Diwakar Mahajan | Marina Danilevsky | Sara Rosenthal
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

Understanding tables is an important and relevant task that involves understanding table structure as well as being able to compare and contrast information within cells. In this paper, we address this challenge by presenting a new dataset and tasks that addresses this goal in a shared task in SemEval 2020 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS). Our dataset contains 981 manually-generated tables and an auto-generated dataset of 1980 tables providing over 180K statement and over 16M evidence annotations. SEM-TAB-FACTS featured two sub-tasks. In sub-task A, the goal was to determine if a statement is supported, refuted or unknown in relation to a table. In sub-task B, the focus was on identifying the specific cells of a table that provide evidence for the statement. 69 teams signed up to participate in the task with 19 successful submissions to subtask A and 12 successful submissions to subtask B. We present our results and main findings from the competition.

pdf bib
Development of an Enterprise-Grade Contract Understanding System
Arvind Agarwal | Laura Chiticariu | Poornima Chozhiyath Raman | Marina Danilevsky | Diman Ghazi | Ankush Gupta | Shanmukha Guttula | Yannis Katsis | Rajasekar Krishnamurthy | Yunyao Li | Shubham Mudgal | Vitobha Munigala | Nicholas Phan | Dhaval Sonawane | Sneha Srinivasan | Sudarshan R. Thitte | Mitesh Vasa | Ramiya Venkatachalam | Vinitha Yaski | Huaiyu Zhu
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

Contracts are arguably the most important type of business documents. Despite their significance in business, legal contract review largely remains an arduous, expensive and manual process. In this paper, we describe TECUS: a commercial system designed and deployed for contract understanding and used by a wide range of enterprise users for the past few years. We reflect on the challenges and design decisions when building TECUS. We also summarize the data science life cycle of TECUS and share lessons learned.

2020

pdf bib
A Survey of the State of Explainable AI for Natural Language Processing
Marina Danilevsky | Kun Qian | Ranit Aharonov | Yannis Katsis | Ban Kawas | Prithviraj Sen
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.

pdf bib
Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification
Prithviraj Sen | Marina Danilevsky | Yunyao Li | Siddhartha Brahma | Matthias Boehm | Laura Chiticariu | Rajasekar Krishnamurthy
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Interpretability of predictive models is becoming increasingly important with growing adoption in the real-world. We present RuleNN, a neural network architecture for learning transparent models for sentence classification. The models are in the form of rules expressed in first-order logic, a dialect with well-defined, human-understandable semantics. More precisely, RuleNN learns linguistic expressions (LE) built on top of predicates extracted using shallow natural language understanding. Our experimental results show that RuleNN outperforms statistical relational learning and other neuro-symbolic methods, and performs comparably with black-box recurrent neural networks. Our user studies confirm that the learned LEs are explainable and capture domain semantics. Moreover, allowing domain experts to modify LEs and instill more domain knowledge leads to human-machine co-creation of models with better performance.

pdf bib
Active Learning for BERT: An Empirical Study
Liat Ein-Dor | Alon Halfon | Ariel Gera | Eyal Shnarch | Lena Dankin | Leshem Choshen | Marina Danilevsky | Ranit Aharonov | Yoav Katz | Noam Slonim
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Real world scenarios present a challenge for text classification, since labels are usually expensive and the data is often characterized by class imbalance. Active Learning (AL) is a ubiquitous paradigm to cope with data scarcity. Recently, pre-trained NLP models, and BERT in particular, are receiving massive attention due to their outstanding performance in various NLP tasks. However, the use of AL with deep pre-trained models has so far received little consideration. Here, we present a large-scale empirical study on active learning techniques for BERT-based classification, addressing a diverse set of AL strategies and datasets. We focus on practical scenarios of binary text classification, where the annotation budget is very small, and the data is often skewed. Our results demonstrate that AL can boost BERT performance, especially in the most realistic scenario in which the initial set of labeled examples is created using keyword-based queries, resulting in a biased sample of the minority class. We release our research framework, aiming to facilitate future research along the lines explored here.

2018

pdf bib
SystemT: Declarative Text Understanding for Enterprise
Laura Chiticariu | Marina Danilevsky | Yunyao Li | Frederick Reiss | Huaiyu Zhu
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)

The rise of enterprise applications over unstructured and semi-structured documents poses new challenges to text understanding systems across multiple dimensions. We present SystemT, a declarative text understanding system that addresses these challenges and has been deployed in a wide range of enterprise applications. We highlight the design considerations and decisions behind SystemT in addressing the needs of the enterprise setting. We also summarize the impact of SystemT on business and education.

pdf bib
DIMSIM: An Accurate Chinese Phonetic Similarity Algorithm Based on Learned High Dimensional Encoding
Min Li | Marina Danilevsky | Sara Noeman | Yunyao Li
Proceedings of the 22nd Conference on Computational Natural Language Learning

Phonetic similarity algorithms identify words and phrases with similar pronunciation which are used in many natural language processing tasks. However, existing approaches are designed mainly for Indo-European languages and fail to capture the unique properties of Chinese pronunciation. In this paper, we propose a high dimensional encoded phonetic similarity algorithm for Chinese, DIMSIM. The encodings are learned from annotated data to separately map initial and final phonemes into n-dimensional coordinates. Pinyin phonetic similarities are then calculated by aggregating the similarities of initial, final and tone. DIMSIM demonstrates a 7.5X improvement on mean reciprocal rank over the state-of-the-art phonetic similarity approaches.

2016

pdf bib
Multilingual Information Extraction with PolyglotIE
Alan Akbik | Laura Chiticariu | Marina Danilevsky | Yonas Kbrom | Yunyao Li | Huaiyu Zhu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

We present PolyglotIE, a web-based tool for developing extractors that perform Information Extraction (IE) over multilingual data. Our tool has two core features: First, it allows users to develop extractors against a unified abstraction that is shared across a large set of natural languages. This means that an extractor needs only be created once for one language, but will then run on multilingual data without any additional effort or language-specific knowledge on part of the user. Second, it embeds this abstraction as a set of views within a declarative IE system, allowing users to quickly create extractors using a mature IE query language. We present PolyglotIE as a hands-on demo in which users can experiment with creating extractors, execute them on multilingual text and inspect extraction results. Using the UI, we discuss the challenges and potential of using unified, crosslingual semantic abstractions as basis for downstream applications. We demonstrate multilingual IE for 9 languages from 4 different language groups: English, German, French, Spanish, Japanese, Chinese, Arabic, Russian and Hindi.

2015

pdf bib
Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling
Alan Akbik | Laura Chiticariu | Marina Danilevsky | Yunyao Li | Shivakumar Vaithyanathan | Huaiyu Zhu
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)