Papers by Bernd Bohnet

11 papers
On Faithfulness and Factuality in Abstractive Summarization (2020.acl-main)

Copied to clipboard

Challenge: Existing conditional text generation models produce unfaithful and unfaithed summaries . current models accomplish a high level of fluency and coherence .
Approach: They propose to use pretrained models for document summarization to better understand hallucinations . they find that textual entailment measures better correlate with faithfulness .
Outcome: The proposed models generate faithful and factual summaries as evaluated by humans.
Coreference Resolution through a seq2seq Transition-Based System (2023.tacl-1)

Copied to clipboard

Challenge: Recent coreference resolution systems use search algorithms to identify mentions and resolve coreference.
Approach: They propose a text-to-text coreference resolution system that uses a semantic paradigm to predict mentions and links jointly.
Outcome: The proposed system achieves state-of-the-art accuracy on CoNLL-2012 datasets with 83.3 F1-score for English, 68.5 F1 score for Arabic, and 74.3 F1 scores for Chinese.
The Second Multilingual Surface Realisation Shared Task (SR’19): Overview and Evaluation Results (D19-63)

Copied to clipboard

Challenge: EMNLP’19 Workshop on Multilingual Surface Realisation aims to stimulate the exploration of advanced neural networks for multilingual sentence generation from Universal Dependency (UD) structures.
Approach: They present results from the SR'19 Shared Task, a multilingual surface realisation task organised as part of the EMNLP'19 Workshop on Multilingual Surface Realisation.
Outcome: The SR'19 shared task was organised as part of the EMNLP'19 Workshop on Multilingual Surface Realisation . it consisted of two tracks with different levels of complexity . the shallow track was offered in eleven, and the deep track in three languages .
A Comprehensive Evaluation of Tool-Assisted Generation Strategies (2023.findings-emnlp)

Copied to clipboard

Challenge: Various few-shot tool-usage strategies have been proposed to overcome LMs' shortcomings.
Approach: They propose to augment language models with tools to overcome their shortcomings . they find strong no-tool baselines are competitive to tool-assisted strategies .
Outcome: The proposed strategies outperform those that refine incorrect outputs with tools in knowledge-retrieval tasks, the study finds . the findings suggest few-shot tool integration is still an open challenge .
A Gold Standard Dependency Treebank for Turkish (2020.lrec-1)

Copied to clipboard

Challenge: Currently, Turkish treebanks are limited due to the limited number of annotated sentences in the domains of Wikipedia and ITU Web Treebanks.
Approach: They propose to annotate Turkish web and Wikipedia sentences for segmentation, morphology, part-of-speech and dependency relations using tagsets and a Wikipedia section.
Outcome: The proposed treebank is the largest publicly available morpho-syntactic treebank in terms of word count and has a dedicated Wikipedia section.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Copied to clipboard

Challenge: Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach: They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome: The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.
Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings (P18-1)

Copied to clipboard

Challenge: recurrent neural networks have produced significant advances in part-of-speech tagging accuracy . a common feature of these models is the presence of rich initial word encodings . however, word or sub-word information interacts only through subsequent recursive layers .
Approach: They propose to use recurrent neural networks with sentence-level context for initial character and word-based representations.
Outcome: The proposed model has the highest accuracy of all participating systems in the CoNLL 2017 task.
A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains (2024.acl-long)

Copied to clipboard

Challenge: Recent literature discusses automatic methods to evaluate reasoning to improve their correctness, but no fine-grained step-level datasets are available to enable thorough evaluation of such verification methods.
Approach: They propose to benchmark automatic verifiers of complex Chain-of-Thought reasoning in open-domain question-answering settings using a dataset that includes comprehensive labels for relevance, attribution to evidence passages, and logical correctness of each reasoning step.
Outcome: The proposed dataset shows that verifiers struggle at verifying reasoning chains, particularly verifying logical correctness and detecting contradictions.
Neural Mention Detection (2020.lrec-1)

Copied to clipboard

Challenge: Mention detection is an important preprocessing step for downstream applications such as NER and coreference resolution.
Approach: They propose and compare three approaches to mention detection using ELMO embeddings and a biaffine classifier.
Outcome: The proposed model outperforms state-of-the-art models on the GENIA corpora and improves on mention recall.
Decoding Part-of-Speech from Human EEG Signals (2022.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that EEG signal magnitude and topography depend on word length, frequency and open vs. closed class.
Approach: They propose to use EEG to predict Part-of-Speech (PoS) tags from neural signals measured at millisecond resolution during text reading.
Outcome: The proposed techniques outperform linear-SVMs on PoS tagging of unigram and bigram data.
Named Entity Recognition as Dependency Parsing (2020.acl-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities.
Approach: They propose a method to handle both types of NEs in one system by using a biaffine dependency parsing model which scores pairs of start and end tokens in a sentence.
Outcome: The proposed model performs well on 8 corpora and achieves accuracy gains of up to 2.2 percentage points.

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