Leshem Choshen


2022

pdf bib
Cluster & Tune: Boost Cold Start Performance in Text Classification
Eyal Shnarch | Ariel Gera | Alon Halfon | Lena Dankin | Leshem Choshen | Ranit Aharonov | Noam Slonim
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as BERT, for a target classification task, is prone to produce poor performance. We suggest a method to boost the performance of such models by adding an intermediate unsupervised classification task, between the pre-training and fine-tuning phases. As such an intermediate task, we perform clustering and train the pre-trained model on predicting the cluster labels.We test this hypothesis on various data sets, and show that this additional classification phase can significantly improve performance, mainly for topical classification tasks, when the number of labeled instances available for fine-tuning is only a couple of dozen to a few hundred.

pdf bib
The Grammar-Learning Trajectories of Neural Language Models
Leshem Choshen | Guy Hacohen | Daphna Weinshall | Omri Abend
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The learning trajectories of linguistic phenomena in humans provide insight into linguistic representation, beyond what can be gleaned from inspecting the behavior of an adult speaker. To apply a similar approach to analyze neural language models (NLM), it is first necessary to establish that different models are similar enough in the generalizations they make. In this paper, we show that NLMs with different initialization, architecture, and training data acquire linguistic phenomena in a similar order, despite their different end performance. These findings suggest that there is some mutual inductive bias that underlies these models’ learning of linguistic phenomena. Taking inspiration from psycholinguistics, we argue that studying this inductive bias is an opportunity to study the linguistic representation implicit in NLMs.Leveraging these findings, we compare the relative performance on different phenomena at varying learning stages with simpler reference models. Results suggest that NLMs exhibit consistent “developmental” stages. Moreover, we find the learning trajectory to be approximately one-dimensional: given an NLM with a certain overall performance, it is possible to predict what linguistic generalizations it has already acquired.Initial analysis of these stages presents phenomena clusters (notably morphological ones), whose performance progresses in unison, suggesting a potential link between the generalizations behind them.

2021

pdf bib
Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
Or Honovich | Leshem Choshen | Roee Aharoni | Ella Neeman | Idan Szpektor | Omri Abend
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability. Inspired by recent work on evaluating factual consistency in abstractive summarization, we propose an automatic evaluation metric for factual consistency in knowledge-grounded dialogue using automatic question generation and question answering. Our metric, denoted Q2, compares answer spans using natural language inference (NLI), instead of token-based matching as done in previous work. To foster proper evaluation, we curate a novel dataset of dialogue system outputs for the Wizard-of-Wikipedia dataset, manually annotated for factual consistency. We perform a thorough meta-evaluation of Q2 against other metrics using this dataset and two others, where it consistently shows higher correlation with human judgements.

pdf bib
Mediators in Determining what Processing BERT Performs First
Aviv Slobodkin | Leshem Choshen | Omri Abend
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Probing neural models for the ability to perform downstream tasks using their activation patterns is often used to localize what parts of the network specialize in performing what tasks. However, little work addressed potential mediating factors in such comparisons. As a test-case mediating factor, we consider the prediction’s context length, namely the length of the span whose processing is minimally required to perform the prediction. We show that not controlling for context length may lead to contradictory conclusions as to the localization patterns of the network, depending on the distribution of the probing dataset. Indeed, when probing BERT with seven tasks, we find that it is possible to get 196 different rankings between them when manipulating the distribution of context lengths in the probing dataset. We conclude by presenting best practices for conducting such comparisons in the future.

2020

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.

pdf bib
Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains
Eyal Shnarch | Leshem Choshen | Guy Moshkowich | Ranit Aharonov | Noam Slonim
Findings of the Association for Computational Linguistics: EMNLP 2020

Approaching new data can be quite deterrent; you do not know how your categories of interest are realized in it, commonly, there is no labeled data at hand, and the performance of domain adaptation methods is unsatisfactory. Aiming to assist domain experts in their first steps into a new task over a new corpus, we present an unsupervised approach to reveal complex rules which cluster the unexplored corpus by its prominent categories (or facets). These rules are human-readable, thus providing an important ingredient which has become in short supply lately - explainability. Each rule provides an explanation for the commonality of all the texts it clusters together. The experts can then identify which rules best capture texts of their categories of interest, and utilize them to deepen their understanding of these categories. These rules can also bootstrap the process of data labeling by pointing at a subset of the corpus which is enriched with texts demonstrating the target categories. We present an extensive evaluation of the usefulness of these rules in identifying target categories, as well as a user study which assesses their interpretability.

pdf bib
Classifying Syntactic Errors in Learner Language
Leshem Choshen | Dmitry Nikolaev | Yevgeni Berzak | Omri Abend
Proceedings of the 24th Conference on Computational Natural Language Learning

We present a method for classifying syntactic errors in learner language, namely errors whose correction alters the morphosyntactic structure of a sentence. The methodology builds on the established Universal Dependencies syntactic representation scheme, and provides complementary information to other error-classification systems. Unlike existing error classification methods, our method is applicable across languages, which we showcase by producing a detailed picture of syntactic errors in learner English and learner Russian. We further demonstrate the utility of the methodology for analyzing the outputs of leading Grammatical Error Correction (GEC) systems.

2019

pdf bib
Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation
Leshem Choshen | Omri Abend
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

We show that the state-of-the-art Transformer MT model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge for the model. Since most dependencies are short-distance, common evaluation metrics will be little influenced by how well systems perform on them. We therefore propose an automatic approach for extracting challenge sets rich with long-distance dependencies, and argue that evaluation using this methodology provides a complementary perspective on system performance. To support our claim, we compile challenge sets for English-German and German-English, which are much larger than any previously released challenge set for MT. The extracted sets are large enough to allow reliable automatic evaluation, which makes the proposed approach a scalable and practical solution for evaluating MT performance on the long-tail of syntactic phenomena.

pdf bib
SemEval-2019 Task 1: Cross-lingual Semantic Parsing with UCCA
Daniel Hershcovich | Zohar Aizenbud | Leshem Choshen | Elior Sulem | Ari Rappoport | Omri Abend
Proceedings of the 13th International Workshop on Semantic Evaluation

We present the SemEval 2019 shared task on Universal Conceptual Cognitive Annotation (UCCA) parsing in English, German and French, and discuss the participating systems and results. UCCA is a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques, as it exhibits reentrancy (resulting in DAG structures), discontinuous structures and non-terminal nodes corresponding to complex semantic units. The shared task has yielded improvements over the state-of-the-art baseline in all languages and settings. Full results can be found in the task’s website https://competitions.codalab.org/competitions/19160.

pdf bib
Learning to combine Grammatical Error Corrections
Yoav Kantor | Yoav Katz | Leshem Choshen | Edo Cohen-Karlik | Naftali Liberman | Assaf Toledo | Amir Menczel | Noam Slonim
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications

The field of Grammatical Error Correction (GEC) has produced various systems to deal with focused phenomena or general text editing. We propose an automatic way to combine black-box systems. Our method automatically detects the strength of a system or the combination of several systems per error type, improving precision and recall while optimizing F-score directly. We show consistent improvement over the best standalone system in all the configurations tested. This approach also outperforms average ensembling of different RNN models with random initializations. In addition, we analyze the use of BERT for GEC - reporting promising results on this end. We also present a spellchecker created for this task which outperforms standard spellcheckers tested on the task of spellchecking. This paper describes a system submission to Building Educational Applications 2019 Shared Task: Grammatical Error Correction. Combining the output of top BEA 2019 shared task systems using our approach, currently holds the highest reported score in the open phase of the BEA 2019 shared task, improving F-0.5 score by 3.7 points over the best result reported.

pdf bib
Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network
Martin Gleize | Eyal Shnarch | Leshem Choshen | Lena Dankin | Guy Moshkowich | Ranit Aharonov | Noam Slonim
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

With the advancement in argument detection, we suggest to pay more attention to the challenging task of identifying the more convincing arguments. Machines capable of responding and interacting with humans in helpful ways have become ubiquitous. We now expect them to discuss with us the more delicate questions in our world, and they should do so armed with effective arguments. But what makes an argument more persuasive? What will convince you? In this paper, we present a new data set, IBM-EviConv, of pairs of evidence labeled for convincingness, designed to be more challenging than existing alternatives. We also propose a Siamese neural network architecture shown to outperform several baselines on both a prior convincingness data set and our own. Finally, we provide insights into our experimental results and the various kinds of argumentative value our method is capable of detecting.

pdf bib
The Language of Legal and Illegal Activity on the Darknet
Leshem Choshen | Dan Eldad | Daniel Hershcovich | Elior Sulem | Omri Abend
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

The non-indexed parts of the Internet (the Darknet) have become a haven for both legal and illegal anonymous activity. Given the magnitude of these networks, scalably monitoring their activity necessarily relies on automated tools, and notably on NLP tools. However, little is known about what characteristics texts communicated through the Darknet have, and how well do off-the-shelf NLP tools do on this domain. This paper tackles this gap and performs an in-depth investigation of the characteristics of legal and illegal text in the Darknet, comparing it to a clear net website with similar content as a control condition. Taking drugs-related websites as a test case, we find that texts for selling legal and illegal drugs have several linguistic characteristics that distinguish them from one another, as well as from the control condition, among them the distribution of POS tags, and the coverage of their named entities in Wikipedia.

2018

pdf bib
Inherent Biases in Reference-based Evaluation for Grammatical Error Correction
Leshem Choshen | Omri Abend
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The prevalent use of too few references for evaluating text-to-text generation is known to bias estimates of their quality (henceforth, low coverage bias or LCB). This paper shows that overcoming LCB in Grammatical Error Correction (GEC) evaluation cannot be attained by re-scaling or by increasing the number of references in any feasible range, contrary to previous suggestions. This is due to the long-tailed distribution of valid corrections for a sentence. Concretely, we show that LCB incentivizes GEC systems to avoid correcting even when they can generate a valid correction. Consequently, existing systems obtain comparable or superior performance compared to humans, by making few but targeted changes to the input. Similar effects on Text Simplification further support our claims.

pdf bib
Automatic Metric Validation for Grammatical Error Correction
Leshem Choshen | Omri Abend
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties in the existing methodology. Experiments with MAEGE shed a new light on metric quality, showing for example that the standard M2 metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analysis of metric behavior, showing that some types of valid edits are consistently penalized by existing metrics.

pdf bib
Will it Blend? Blending Weak and Strong Labeled Data in a Neural Network for Argumentation Mining
Eyal Shnarch | Carlos Alzate | Lena Dankin | Martin Gleize | Yufang Hou | Leshem Choshen | Ranit Aharonov | Noam Slonim
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

The process of obtaining high quality labeled data for natural language understanding tasks is often slow, error-prone, complicated and expensive. With the vast usage of neural networks, this issue becomes more notorious since these networks require a large amount of labeled data to produce satisfactory results. We propose a methodology to blend high quality but scarce strong labeled data with noisy but abundant weak labeled data during the training of neural networks. Experiments in the context of topic-dependent evidence detection with two forms of weak labeled data show the advantages of the blending scheme. In addition, we provide a manually annotated data set for the task of topic-dependent evidence detection. We believe that blending weak and strong labeled data is a general notion that may be applicable to many language understanding tasks, and can especially assist researchers who wish to train a network but have a small amount of high quality labeled data for their task of interest.

pdf bib
Reference-less Measure of Faithfulness for Grammatical Error Correction
Leshem Choshen | Omri Abend
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

We propose USim, a semantic measure for Grammatical Error Correction (that measures the semantic faithfulness of the output to the source, thereby complementing existing reference-less measures (RLMs) for measuring the output’s grammaticality. USim operates by comparing the semantic symbolic structure of the source and the correction, without relying on manually-curated references. Our experiments establish the validity of USim, by showing that the semantic structures can be consistently applied to ungrammatical text, that valid corrections obtain a high USim similarity score to the source, and that invalid corrections obtain a lower score.