Papers by Nils Reimers

16 papers
Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution (P19-1)

Copied to clipboard

Challenge: Recognizing that various textual spans across multiple texts refer to the same entity or event is an important NLP task.
Approach: They propose a neural architecture for cross-document coreference resolution by representing an event mention using its lexical span, surrounding context, and relation to other mentions via predicate-arguments structures.
Outcome: The proposed model outperforms the state-of-the-art event coreference model on ECB+ while providing the first entity coreference results on this corpus.
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks (2021.naacl-main)

Copied to clipboard

Challenge: Cross-encoders perform full-attention over the input pair, while bi-encoding requires substantial training data and fine-tuning over the target task to achieve competitive performance.
Approach: They propose a data augmentation strategy that uses cross-encoders to label larger set of input pairs to augment training data for bi-encoding.
Outcome: The proposed approach improves on multiple tasks and domain adaptation tasks by up to 37 points compared to the original bi-encoder performance.
Triple-Encoders: Representations That Fire Together, Wire Together (2024.acl-long)

Copied to clipboard

Challenge: Existing search-based dialog models re-encode the dialog history at every turn, causing high cost.
Approach: They propose a method that encodes relative distances between utterances via a bi-encoder . they use a hebbian-inspired co-occurrence learning objective to compute distributed utterrance mixtures .
Outcome: The proposed method improves on bi-encoded utterances and even better generalization . it can encode 2020 and Erker et al. (2023) with the same results.
Classification and Clustering of Arguments with Contextualized Word Embeddings (P19-1)

Copied to clipboard

Challenge: Existing methods for argument mining focus on analyzing local argumentation structures, but information-seeking approaches need to be able to deal with heterogeneous sources and topics.
Approach: They propose to use contextualized word embeddings to classify and cluster topic-dependent arguments using a UKP Sentential Argument Mining Corpus and IBM Debater - Evidence Sentences datasets.
Outcome: The proposed method improves state-of-the-art on argument classification and clustering tasks and across multiple datasets.
Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking (2022.emnlp-main)

Copied to clipboard

Challenge: Extensive experiments demonstrate that integrating relevance feedback directly into neural re-ranking models improves their performance.
Approach: They propose a kNN approach that re-ranks documents based on their similarity with the query and the documents the user considers relevant.
Outcome: The proposed approach outperforms all other methods by 5.2% on large-scale information retrieval datasets.
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (D19-1)

Copied to clipboard

Challenge: Existing methods for finding similar sentences require multiple inferences . a modern GPU requires 65 hours to find the most similar pair in 10,000 sentences .
Approach: They propose a modification of the pretrained BERT network that uses siamese and triplet networks to derive semantically meaningful sentence embeddings.
Outcome: The proposed method outperforms existing methods on sentence-pair regression tasks.
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to learn sentence embeddings require labeled data, but it is expensive.
Approach: They propose an unsupervised method which learns sentence embeddings using unlabeled data . they propose a transformer-based sequence denoising auto-encoder which can be used for training .
Outcome: The proposed method outperforms existing methods on four datasets from heterogeneous domains.
AdapterDrop: On the Efficiency of Adapters in Transformers (2021.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to transformer models are expensive to fine-tune, slow for inference, and have large storage requirements.
Approach: They propose a method to remove adapters from transformer layers during training and inference . they show that AdapterDrop can dynamically reduce computational overhead .
Outcome: The proposed approach reduces computational overhead while maintaining performance over multiple tasks with minimal loss of performance.
GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval (2026.eacl-long)

Copied to clipboard

Challenge: Decomposition-based multi-hop retrieval methods rely on autoregressive steps to break down complex queries, which breaks end-to-end differentiability and is computationally expensive.
Approach: They propose a multi-hop dense retrieval model that integrates causal language modeling with dense retrievals.
Outcome: The proposed model outperforms existing methods on in-distribution and out-of-difference benchmarks.
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval (2022.naacl-main)

Copied to clipboard

Challenge: Dense retrieval approaches suffer from the lexical gap and require large amounts of training data.
Approach: They propose an unsupervised method for domain adaptation that uses query generator and pseudo labeling from a cross-encoder to improve retrieval performance.
Outcome: The proposed method outperforms state-of-the-art retrieval methods on domain-specialized datasets by 9.3 points nDCG@10 on six tasks.
DAPR: A Benchmark on Document-Aware Passage Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Recent approaches to retrieve short passages are limited due to expensive operations such as selfattention.
Approach: They propose to use a task to find passages from a large corpus of documents . they extend the SoTA passage retrievers with document context to achieve this task .
Outcome: The proposed task is called Document-Aware Passage Retrieval (DAPR) it performs best on easy and hard queries, but fails on hard queries requiring document-context understanding .
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing sentence embeddings models are monolingual, and only for English . a new method allows to create multilingual versions from monolingual models .
Approach: They propose a method to extend existing sentence embedding models to new languages . they use a translated sentence to generate sentence embeds for the source language .
Outcome: The proposed method improves accuracy for multilingual setups and languages.
MTEB: Massive Text Embedding Benchmark (2023.eacl-main)

Copied to clipboard

Challenge: Existing text embeddings are evaluated on a small set of datasets, not covering their possible applications to other tasks.
Approach: They propose a benchmarking framework that evaluates 8 embedding tasks covering 58 datasets and 112 languages.
Outcome: The proposed model is the most comprehensive benchmark of text embeddings to date.
Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval (2022.tacl-1)

Copied to clipboard

Challenge: Current approaches to cross-modal retrieval process text and visual input jointly . current approaches are pretrained from scratch and suffer from huge retrieval latency and inefficiency issues .
Approach: They propose a cooperative retrieve-and-rerank framework that turns pretrained text-image multi-modal models into efficient retrieval models.
Outcome: The proposed framework improves retrieval performance over current approaches . it uses twin networks to encode all items of a corpus and a cross-encoder component for a more nuanced ranking .
UKP-SQUARE: An Online Platform for Question Answering Research (2022.acl-demo)

Copied to clipboard

Challenge: Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats and require different model architectures and setups.
Approach: They propose an extensible online QA platform that allows users to query and analyze a large collection of modern Skills via a user-friendly web interface and integrated behavioural tests.
Outcome: The proposed tool allows users to query and analyze a large collection of modern Skills via a user-friendly web interface and integrated behavioural tests.
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes (2021.acl-short)

Copied to clipboard

Challenge: Existing studies have shown that dense representations outperform sparse representations with large index sizes.
Approach: They propose to use dense low-dimensional representations to retrieve relevant documents . they show performance decreases quicker for increasing index sizes than for sparse representations .
Outcome: The proposed representations outperform sparse representations with large index sizes.

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