Search Results for author: Noam Slonim

Found 71 papers, 14 papers with code

Active Learning for BERT: An Empirical Study

1 code implementation EMNLP 2020 Liat Ein-Dor, Alon Halfon, Ariel Gera, Eyal Shnarch, Lena Dankin, Leshem Choshen, Marina Danilevsky, Ranit Aharonov, Yoav Katz, Noam Slonim

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.

Active Learning Binary text classification +3

Efficient Benchmarking of Language Models

no code implementations22 Aug 2023 Yotam Perlitz, Elron Bandel, Ariel Gera, Ofir Arviv, Liat Ein-Dor, Eyal Shnarch, Noam Slonim, Michal Shmueli-Scheuer, Leshem Choshen

Based on our findings we outline a set of concrete recommendations for more efficient benchmark design and utilization practices leading to dramatic cost savings with minimal loss of benchmark reliability often reducing computation by x100 or more.

Benchmarking

Active Learning for Natural Language Generation

no code implementations24 May 2023 Yotam Perlitz, Ariel Gera, Michal Shmueli-Scheuer, Dafna Sheinwald, Noam Slonim, Liat Ein-Dor

In this paper, we present a first systematic study of active learning for NLG, considering a diverse set of tasks and multiple leading selection strategies, and harnessing a strong instruction-tuned model.

Active Learning text-classification +2

The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers

1 code implementation2 May 2023 Ariel Gera, Roni Friedman, Ofir Arviv, Chulaka Gunasekara, Benjamin Sznajder, Noam Slonim, Eyal Shnarch

Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative.

Language Modelling Text Generation

Knowledge is a Region in Weight Space for Fine-tuned Language Models

no code implementations9 Feb 2023 Almog Gueta, Elad Venezian, Colin Raffel, Noam Slonim, Yoav Katz, Leshem Choshen

Notably, we show that language models that have been finetuned on the same dataset form a tight cluster in the weight space, while models finetuned on different datasets from the same underlying task form a looser cluster.

SimpleStyle: An Adaptable Style Transfer Approach

no code implementations20 Dec 2022 Elron Bandel, Yoav Katz, Noam Slonim, Liat Ein-Dor

We offer our protocol as a simple yet strong baseline for works that wish to make incremental advancements in the field of attribute controlled text rewriting.

Attribute Denoising +2

Where to start? Analyzing the potential value of intermediate models

no code implementations31 Oct 2022 Leshem Choshen, Elad Venezian, Shachar Don-Yehia, Noam Slonim, Yoav Katz

Such a model, finetuned on some source dataset, may provide a better starting point for a new finetuning process on a desired target dataset.

Zero-Shot Text Classification with Self-Training

1 code implementation31 Oct 2022 Ariel Gera, Alon Halfon, Eyal Shnarch, Yotam Perlitz, Liat Ein-Dor, Noam Slonim

Recent advances in large pretrained language models have increased attention to zero-shot text classification.

Natural Language Inference text-classification +2

VIRATrustData: A Trust-Annotated Corpus of Human-Chatbot Conversations About COVID-19 Vaccines

no code implementations24 May 2022 Roni Friedman, João Sedoc, Shai Gretz, Assaf Toledo, Rose Weeks, Naor Bar-Zeev, Yoav Katz, Noam Slonim

Public trust in medical information is crucial for successful application of public health policies such as vaccine uptake.

Chatbot

Diversity Enhanced Table-to-Text Generation via Type Control

no code implementations22 May 2022 Yotam Perlitz, Liat Ein-Dor, Dafna Sheinwald, Noam Slonim, Michal Shmueli-Scheuer

Generating natural language statements to convey logical inferences from tabular data (i. e., Logical NLG) is a process with one input and a variety of valid outputs.

Table-to-Text Generation valid +1

Multi-Domain Targeted Sentiment Analysis

no code implementations NAACL 2022 Orith Toledo-Ronen, Matan Orbach, Yoav Katz, Noam Slonim

Our results and analysis show that our approach is a promising step towards a practical domain-robust TSA system.

Sentiment Analysis

Fusing finetuned models for better pretraining

2 code implementations6 Apr 2022 Leshem Choshen, Elad Venezian, Noam Slonim, Yoav Katz

We also show that fusing is often better than intertraining.

Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization

no code implementations29 Mar 2022 Benjamin Sznajder, Chulaka Gunasekara, Guy Lev, Sachin Joshi, Eyal Shnarch, Noam Slonim

We observe that there are different heuristics that are associated with summaries of different perspectives, and explore these heuristics to create weak-labeled data for intermediate training of the models before fine-tuning with scarce human annotated summaries.

Decision Making

Quality Controlled Paraphrase Generation

1 code implementation ACL 2022 Elron Bandel, Ranit Aharonov, Michal Shmueli-Scheuer, Ilya Shnayderman, Noam Slonim, Liat Ein-Dor

Furthermore, we suggest a method that given a sentence, identifies points in the quality control space that are expected to yield optimal generated paraphrases.

Paraphrase Generation Sentence

Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis

1 code implementation6 Jan 2022 Liat Ein-Dor, Ilya Shnayderman, Artem Spector, Lena Dankin, Ranit Aharonov, Noam Slonim

In recent years, pretrained language models have revolutionized the NLP world, while achieving state of the art performance in various downstream tasks.

Continual Pretraining Sentiment Analysis

Overview of the 2021 Key Point Analysis Shared Task

no code implementations EMNLP (ArgMining) 2021 Roni Friedman, Lena Dankin, Yufang Hou, Ranit Aharonov, Yoav Katz, Noam Slonim

We describe the 2021 Key Point Analysis (KPA-2021) shared task on key point analysis that we organized as a part of the 8th Workshop on Argument Mining (ArgMining 2021) at EMNLP 2021.

Argument Mining Text Summarization

Project Debater APIs: Decomposing the AI Grand Challenge

no code implementations EMNLP (ACL) 2021 Roy Bar-Haim, Yoav Kantor, Elad Venezian, Yoav Katz, Noam Slonim

Engaging in a live debate requires a diverse set of skills, and Project Debater has been developed accordingly as a collection of components, each designed to perform a specific subtask.

Argument Mining

Advances in Debating Technologies: Building AI That Can Debate Humans

no code implementations ACL 2021 Roy Bar-Haim, Liat Ein-Dor, Matan Orbach, Elad Venezian, Noam Slonim

We present a complete pipeline of a debating system, and discuss the information flow and the interaction between the various components.

Argument Mining Stance Classification

Every Bite Is an Experience: Key Point Analysis of Business Reviews

no code implementations ACL 2021 Roy Bar-Haim, Lilach Eden, Yoav Kantor, Roni Friedman, Noam Slonim

Previous work on review summarization focused on measuring the sentiment toward the main aspects of the reviewed product or business, or on creating a textual summary.

Sentiment Analysis

Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification

no code implementations1 Jan 2021 Eyal Shnarch, Ariel Gera, Alon Halfon, Lena Dankin, Leshem Choshen, Ranit Aharonov, Noam Slonim

In such low resources scenarios, we suggest performing an unsupervised classification task prior to fine-tuning on the target task.

Clustering General Classification +2

Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains

no code implementations Findings of the Association for Computational Linguistics 2020 Eyal Shnarch, Leshem Choshen, Guy Moshkowich, Noam Slonim, Ranit Aharonov

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.

Domain Adaptation

Multilingual Argument Mining: Datasets and Analysis

no code implementations Findings of the Association for Computational Linguistics 2020 Orith Toledo-Ronen, Matan Orbach, Yonatan Bilu, Artem Spector, Noam Slonim

The growing interest in argument mining and computational argumentation brings with it a plethora of Natural Language Understanding (NLU) tasks and corresponding datasets.

Argument Mining Machine Translation +3

The workweek is the best time to start a family -- A Study of GPT-2 Based Claim Generation

no code implementations Findings of the Association for Computational Linguistics 2020 Shai Gretz, Yonatan Bilu, Edo Cohen-Karlik, Noam Slonim

Argument generation is a challenging task whose research is timely considering its potential impact on social media and the dissemination of information.

Retrieval

Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis

2 code implementations EMNLP 2020 Roy Bar-Haim, Yoav Kantor, Lilach Eden, Roni Friedman, Dan Lahav, Noam Slonim

Recent work has proposed to summarize arguments by mapping them to a small set of expert-generated key points, where the salience of each key point corresponds to the number of its matching arguments.

Document Summarization Key Point Matching +1

What if we had no Wikipedia? Domain-independent Term Extraction from a Large News Corpus

no code implementations17 Sep 2020 Yonatan Bilu, Shai Gretz, Edo Cohen, Noam Slonim

One of the most impressive human endeavors of the past two decades is the collection and categorization of human knowledge in the free and accessible format that is Wikipedia.

Benchmarking Term Extraction

From Arguments to Key Points: Towards Automatic Argument Summarization

no code implementations ACL 2020 Roy Bar-Haim, Lilach Eden, Roni Friedman, Yoav Kantor, Dan Lahav, Noam Slonim

Generating a concise summary from a large collection of arguments on a given topic is an intriguing yet understudied problem.

A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis

2 code implementations26 Nov 2019 Shai Gretz, Roni Friedman, Edo Cohen-Karlik, Assaf Toledo, Dan Lahav, Ranit Aharonov, Noam Slonim

To this end, we created a corpus of 30, 497 arguments carefully annotated for point-wise quality, released as part of this work.

Financial Event Extraction Using Wikipedia-Based Weak Supervision

no code implementations WS 2019 Liat Ein-Dor, Ariel Gera, Orith Toledo-Ronen, Alon Halfon, Benjamin Sznajder, Lena Dankin, Yonatan Bilu, Yoav Katz, Noam Slonim

Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more recent works employing machine learning techniques.

BIG-bench Machine Learning Event Extraction

Automatic Argument Quality Assessment -- New Datasets and Methods

no code implementations3 Sep 2019 Assaf Toledo, Shai Gretz, Edo Cohen-Karlik, Roni Friedman, Elad Venezian, Dan Lahav, Michal Jacovi, Ranit Aharonov, Noam Slonim

In spite of the inherent subjective nature of the task, both annotation schemes led to surprisingly consistent results.

Language Modelling

Argument Invention from First Principles

no code implementations ACL 2019 Yonatan Bilu, Ariel Gera, Daniel Hershcovich, Benjamin Sznajder, Dan Lahav, Guy Moshkowich, Anael Malet, Assaf Gavron, Noam Slonim

In this work we aim to explicitly define a taxonomy of such principled recurring arguments, and, given a controversial topic, to automatically identify which of these arguments are relevant to the topic.

Controversy in Context

no code implementations20 Aug 2019 Benjamin Sznajder, Ariel Gera, Yonatan Bilu, Dafna Sheinwald, Ella Rabinovich, Ranit Aharonov, David Konopnicki, Noam Slonim

With the growing interest in social applications of Natural Language Processing and Computational Argumentation, a natural question is how controversial a given concept is.

Towards Effective Rebuttal: Listening Comprehension using Corpus-Wide Claim Mining

no code implementations WS 2019 Tamar Lavee, Matan Orbach, Lili Kotlerman, Yoav Kantor, Shai Gretz, Lena Dankin, Shachar Mirkin, Michal Jacovi, Yonatan Bilu, Ranit Aharonov, Noam Slonim

To this end, we collected a large dataset of $400$ speeches in English discussing $200$ controversial topics, mined claims for each topic, and asked annotators to identify the mined claims mentioned in each speech.

Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network

no code implementations ACL 2019 Martin Gleize, Eyal Shnarch, Leshem Choshen, Lena Dankin, Guy Moshkowich, Ranit Aharonov, Noam Slonim

With the advancement in argument detection, we suggest to pay more attention to the challenging task of identifying the more convincing arguments.

Syntactic Interchangeability in Word Embedding Models

1 code implementation WS 2019 Daniel Hershcovich, Assaf Toledo, Alon Halfon, Noam Slonim

Nearest neighbors in word embedding models are commonly observed to be semantically similar, but the relations between them can vary greatly.

POS valid +1

Learning Concept Abstractness Using Weak Supervision

no code implementations EMNLP 2018 Ella Rabinovich, Benjamin Sznajder, Artem Spector, Ilya Shnayderman, Ranit Aharonov, David Konopnicki, Noam Slonim

We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data.

Towards an argumentative content search engine using weak supervision

no code implementations COLING 2018 Ran Levy, Ben Bogin, Shai Gretz, Ranit Aharonov, Noam Slonim

Our results clearly indicate that the system is able to successfully generalize from the weak signal, outperforming previously reported results in terms of both precision and coverage.

Argument Mining Decision Making +1

A Recorded Debating Dataset

no code implementations LREC 2018 Shachar Mirkin, Michal Jacovi, Tamar Lavee, Hong-Kwang Kuo, Samuel Thomas, Leslie Sager, Lili Kotlerman, Elad Venezian, Noam Slonim

This paper describes an English audio and textual dataset of debating speeches, a unique resource for the growing research field of computational argumentation and debating technologies.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Unsupervised corpus--wide claim detection

no code implementations WS 2017 Ran Levy, Shai Gretz, Benjamin Sznajder, Shay Hummel, Ranit Aharonov, Noam Slonim

Automatic claim detection is a fundamental argument mining task that aims to automatically mine claims regarding a topic of consideration.

Argument Mining Decision Making +1

GRASP: Rich Patterns for Argumentation Mining

no code implementations EMNLP 2017 Eyal Shnarch, Ran Levy, Vikas Raykar, Noam Slonim

A human observer may notice the following underlying common structure, or pattern: [someone][argue/suggest/state][that][topic term][sentiment term].

Document Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.