Papers with MIT

31 papers
BERTweet: A pre-trained language model for English Tweets (2020.emnlp-demos)

Copied to clipboard

Challenge: Experiments show that BERTweet outperforms strong baselines RoBERTa-base and XLM-R-base on three Tweet NLP tasks: Part-of-speech tagging, Named-entity recognition and text classification.
Approach: They propose to train a pre-trained language model for English Tweets using the RoBERTa pre training procedure and use it to train the model.
Outcome: Experiments show that the model outperforms baseline models on three Tweet NLP tasks: Part-of-speech tagging, Named-entity recognition and text classification.
Web-based Annotation Interface for Derivational Morphology (2022.naacl-demo)

Copied to clipboard

Challenge: a visual interface for manual annotation of language resources for derivational morphology is created using relatively simple programming techniques.
Approach: They propose a web-based visual interface for manual annotation of language resources for derivational morphology.
Outcome: The proposed interface can be used for manual annotation of derivational morphology resources.
NLP Workbench: Efficient and Extensible Integration of State-of-the-art Text Mining Tools (2023.eacl-demo)

Copied to clipboard

Challenge: NLP Workbench is a web-based text mining platform that allows non-expert users to obtain semantic understanding of large-scale corpora using state-of-the-art text mining models.
Approach: They propose to use a microservice architecture to replace existing models or integrate a new one.
Outcome: The proposed model is extensible and can be easily replaced or integrated with existing models.
BME-UW at SRST-2019: Surface realization with Interpreted Regular Tree Grammars (D19-63)

Copied to clipboard

Challenge: adaamko's system restores word order and inflection from a graph of typed, directed dependencies between lemmas.
Approach: They propose a method that restores word order and inflection from a graph of typed, directed dependencies between lemmas.
Outcome: The proposed system restores word order and inflection from a graph of typed, directed dependencies between lemmas.
TransIns: Document Translation with Markup Reinsertion (2021.emnlp-demo)

Copied to clipboard

Challenge: MT models cannot translate complex formatted documents, as markup can be nested, apply to spans contiguous in source but non-contiguous.
Approach: They propose a system for non-plain text document translation that reinserts markup into translated sentences using token alignments between source and target sentences.
Outcome: The proposed system outperforms translation services in terms of markup quality . it integrates token alignments between source and target sentences to reinsert markup . the proposed system is available under the MIT license .
Loki: An Open-Source Tool for Fact Verification (2025.coling-demos)

Copied to clipboard

Challenge: Loki is an open-source fact-checking tool designed to address the growing problem of misinformation.
Approach: They propose a tool that breaks down the fact-checking task into five steps . they propose LOKI, which offers a semiautomated, human-in-the-loop approach .
Outcome: a new open-source tool is designed to address the growing problem of misinformation . the tool breaks down the fact-checking task into five steps to assist human judgment .
Small-Text: Active Learning for Text Classification in Python (2023.eacl-demo)

Copied to clipboard

Challenge: small-text is an easy-to-use active learning library for text classification . it features a variety of pre-implemented state-of-the-art query strategies and stopping criteria .
Approach: They introduce small-text, an easy-to-use active learning library for Python . it offers pool-based active learning for single- and multi-label text classification . they find it matches vanilla transformer fine-tuning in terms of classification accuracy .
Outcome: The proposed library outperforms vanilla transformer fine-tuning in classification accuracy and area under the curve.
ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems (2024.emnlp-demo)

Copied to clipboard

Challenge: Recent studies show that large language models can be used to construct complex multi-agent systems.
Approach: They propose a toolkit for recursive multi-agent systems that supports custom tool-use, delegation schemes, event-based logging, and interactive replay.
Outcome: The proposed tool achieves significant performance gains on agentic benchmarks and identify potential areas of improvement through visualization and debugging tools.
stopes - Modular Machine Translation Pipelines (2022.emnlp-demos)

Copied to clipboard

Challenge: Neural machine translation is a natural language deep learning application that needs data to be trained.
Approach: They describe a framework that empowers scalability and versatility for research use cases.
Outcome: The proposed framework empowers scalability and versatility for research use cases.
Hindsight: Structured Agent Memory that Retains, Recalls, and Reflects (2026.acl-demo)

Copied to clipboard

Challenge: Hindsight organizes long-term memory into four logical networks and exposes three core operations.
Approach: Hindsight organizes long-term memory into four logical networks and exposes three core operations.
Outcome: Hindsight is a working memory system for AI agents that separates facts from beliefs . the system outperforms existing models on LongMemEval and LoCoMo with 83.6% accuracy .
ExplainaBoard: An Explainable Leaderboard for NLP (2021.acl-demo)

Copied to clipboard

Challenge: Using leaderboards, researchers can track the performance of various systems on various NLP tasks.
Approach: They propose a new conceptualization and implementation of NLP evaluation using a leaderboard.
Outcome: The ExplainaBoard is an evaluation tool for natural language processing (NLP) it covers more than 400 systems, 50 datasets, 40 languages, and 12 tasks.
MASEval: Extending Multi-Agent Evaluation from Models to Systems (2026.acl-demo)

Copied to clipboard

Challenge: MASEval provides a framework-agnostic, system-level comparison across any agent framework and benchmark.
Approach: They propose a Python library that treats the entire agentic system as the unit of analysis.
Outcome: The proposed framework treats the entire agentic system as the unit of analysis.
TokCollate: A Comprehensive Tool for Tokenizer Evaluation and Visualization across Languages (2026.acl-demo)

Copied to clipboard

Challenge: Tokenization quality varies significantly across languages, leading to disparities in LLM performance and cost for speakers of less-resourced languages.
Approach: They propose a Python-based evaluation framework and a JavaScript visualization interface that evaluates tokenizers in a variety of languages.
Outcome: TokCollate is an evaluation framework for tokenizers with a JavaScript visualization interface.
ALToolbox: A Set of Tools for Active Learning Annotation of Natural Language Texts (2022.emnlp-demos)

Copied to clipboard

Challenge: Currently, the framework supports text classification, sequence tagging, and seq2seq tasks.
Approach: They propose an open-source framework for active learning annotation in natural language processing that provides an easy-to-deploy GUI annotation tool directly in the Jupyter IDE.
Outcome: The proposed framework reduces computational overhead and duration of AL iterations and increases annotated data reusability.
gec-metrics: A Unified Library for Grammatical Error Correction Evaluation (2025.acl-demo)

Copied to clipboard

Challenge: a library for using and developing grammatical error correction (GEC) evaluation metrics is released under the MIT license .
Approach: They propose a library for using and developing grammatical error correction (GEC) evaluation metrics through a unified interface.
Outcome: The proposed method is based on a unified evaluation framework with a strong focus on API usage and extensible.
KWJA: A Unified Japanese Analyzer Based on Foundation Models (2023.acl-demo)

Copied to clipboard

Challenge: KWJA supports a wide range of tasks including typo correction, word segmentation, word normalization, named entity recognition, dependency parsing, PAS analysis, bridging reference resolution, coreference resolution, and discourse relation analysis.
Approach: They propose to build a Japanese text analyzer based on foundation models that performs a wide range of tasks.
Outcome: The proposed model performs better in a multi-task manner than other analyzers with specialized models.
The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration (2025.emnlp-demos)

Copied to clipboard

Challenge: Large Language Model (LLM)-integrated applications are becoming more popular to support, augment, and automate tasks.
Approach: They propose to embed universal adversarial triggers in webpage HTML to hijack agents . they also use a browser-gym agent powered by Llama-3.1 to test their system .
Outcome: The proposed system software is released under the MIT License .
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning (2026.acl-demo)

Copied to clipboard

Challenge: Existing TTC scaling strategies and reasoning scorers are fragmented and evaluated under inconsistent protocols.
Approach: They propose a framework for seamless test-time compute scaling of large language model reasoning . they use a modular Python library to implement state-of-the-art scaling strategy and scorer families .
Outcome: The proposed framework evaluates performance and computational efficiency on mathematical and coding tasks.
Template-Based Named Entity Recognition Using BART (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for fewshot NER do not make full use of knowledge transfer in NER model parameters.
Approach: They propose a template-based method for NER that treats NER as a language model ranking problem in a sequence-to-sequence framework.
Outcome: The proposed method achieves 92.55% F1 score on the CoNLL03 task and significantly better than fine-tuning BERT 10.88%, 15.34%, and 11.73% F1 scores on the MIT Movie, the ATIS, and the MATLAB task.
LMUNIT: Fine-grained Evaluation with Natural Language Unit Tests (2025.findings-emnlp)

Copied to clipboard

Challenge: Using natural language unit tests, language models are costly and noisy, and automated metrics provide only coarse, difficult-to-interpret signals.
Approach: They propose a paradigm that decomposes response quality into explicit, testable criteria and a unified scoring model, LMUnit, which combines multi-objective training across preferences, direct ratings, and natural language rationales.
Outcome: The proposed paradigm significantly improves inter-annotator agreement and enables more effective LLM development workflows.
Multilingual Open Text Release 1: Public Domain News in 44 Languages (2022.lrec-1)

Copied to clipboard

Challenge: a corpus of permissively licensed text is being developed in 44 languages, many of which have limited existing text resources for natural language processing.
Approach: They propose to create a multilingual corpus containing text in 44 languages . they describe their process for collecting, filtering, and processing the data .
Outcome: The first release of the corpus contains over 2.8 million news articles and an additional 1 million short snippets published between 2001–2022 and collected from Voice of America news websites.
ReCoT-NER: Enhancing Zero-Shot Named Entity Recognition through Chain-of-Thought Prompting and Recall-Oriented Loss Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a key component of natural language processing (NLP) but it is difficult to implement in specialized domains such as wind power fault diagnosis.
Approach: They propose a reasoning-enhanced generative framework that integrates Chain-of-Thought prompting and recall-oriented loss optimization to address these challenges.
Outcome: The proposed framework improves recall and overall F1 performance across general and industrial domains.
CILex: An Investigation of Context Information for Lexical Substitution Methods (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for lexical substitution rely on manually curated lexicals and contextual word embedding models.
Approach: They propose a method that uses contextual sentence embeddings to generate substitutes for a target word given a context and a model that captures additional context information complimenting contextual word embedders.
Outcome: The proposed method is state-of-the-art on the widely used LS07 and CoInCo datasets with P@1 scores of 55.96% and 57.25% for lexical substitution.
Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable advancements in specialized fields such as finance, law, and medicine.
Approach: They propose to provide datasets covering all major training stages including pretraining, instruction fine-tuning, and reasoning distillation with cybersecurity-specific self-reflection data.
Outcome: Extensive ablation studies show that LLMs acquire their knowledge during pretraining, while reasoning distillation leads to a 15% gain in security certification (CISSP).
Web-based Annotation Tool for Inflectional Language Resources (L18-1)

Copied to clipboard

Challenge: Wasim is a web-based tool for semi-automatic morphosyntactic annotation of inflectional languages.
Approach: They present a web-based tool for semi-automatic morphosyntactic annotation of inflectional languages resources.
Outcome: The tool has high flexibility in segmenting tokens, editing, diacritizing, labelling tokens and segments.
A New Aligned Simple German Corpus (2023.acl-long)

Copied to clipboard

Challenge: “Leichte Sprache” is a regulated language aimed to facilitate complex written language that would otherwise stay inaccessible to different groups of people.
Approach: They propose to use automatic sentence-alignment methods to align multiple document-aligned sources to improve their sentence alignments.
Outcome: The proposed dataset outperforms previous work and is available under MIT license.
Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation (2024.emnlp-main)

Copied to clipboard

Challenge: Sentence segmentation is a key task in many NLP systems, but no prior method has achieved all of the features needed to segment a text into sentences.
Approach: They propose a new model that uses punctuation to enhance robustness and adaptability.
Outcome: The proposed model outperforms baselines across 8 corpora across diverse domains and languages and is available under the MIT license.
Gramble: A Tabular Programming Language for Collaborative Linguistic Modeling (2024.lrec-main)

Copied to clipboard

Challenge: a new programming language for linguistic parsing and generation is available for free . a cross-platform interpreter is available on the web via google sheets .
Approach: a new Gramble programming language is being developed for linguistic parsing and generation . the language is a domain-specific programming language that supports live group programming . a cross-platform interpreter is available for Windows, MacOS, and UNIX .
Outcome: a new programming language for linguistic parsing and generation is released under the MIT license . the language is based on handwritten declarative code rather than machine learning .
TopicNet: Making Additive Regularisation for Topic Modelling Accessible (2020.lrec-1)

Copied to clipboard

Challenge: TopicNet is a Python module for topic modeling.
Approach: They introduce a Python module for topic modeling that brings regularization topic modeling to non-specialists using a general-purpose language.
Outcome: The proposed module aims to bring topic modeling to non-specialists using a general-purpose language.
MaintIE: A Fine-Grained Annotation Schema and Benchmark for Information Extraction from Maintenance Short Texts (2024.lrec-main)

Copied to clipboard

Challenge: Maintenance short texts (MSTs) provide crucial insights into the state and maintenance activities of machines, infrastructure, and other engineered assets.
Approach: They propose a multi-level fine-grained annotation scheme for entity recognition and relation extraction that includes 5 top-level classes and 6 relations tailored to MSTs.
Outcome: The proposed scheme provides high-quality, fine-grained annotations and a coarse-grain corpus of 7,000 texts.
GottBERT: a pure German Language Model (2024.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models have advanced natural language processing (NLP) despite the introduction of BERT, single-language models are still relevant.
Approach: They present a German singlelanguage RoBERT model pre-trained exclusively on the German portion of the OSCAR dataset.
Outcome: The GottBERT model outperforms the existing models on Named Entity Recognition and text classification tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations