Papers by Michael Elhadad
Cross-Lingual UMLS Named Entity Linking using UMLS Dictionary Fine-Tuning (2022.findings-acl)
Copied to clipboard
| Challenge: | a new method for named entity linking is being developed in the field of public health . it uses an offline unsupervised construction of a translated dictionary and a pre-trained transformer language model to filter candidates according to context. |
| Approach: | They propose a method for mapping mentions in a source language to UMLS concepts . they extend an offline unsupervised translation of a translated UMLS dictionary . |
| Outcome: | The proposed approach achieves state-of-the-art on the Hebrew Camoni corpus and English datasets. |
Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing semantic role labeling resources for Hebrew are not available in English. |
| Approach: | They propose a semantic role labeling resource for Hebrew built semi-automatically through annotation projection from English to Hebrew. |
| Outcome: | The proposed resource is built semi-automatically from an English dataset . it includes morphological analysis, dependency syntax and semantic role labeling . |
Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that supervised models exploit data artifacts to achieve good test scores while their performance severely degrades on samples outside their training distribution. |
| Approach: | They propose a method which automatically generates contrast sets for the visual question answering task by using a semantic input representation. |
| Outcome: | The proposed method computes the answer of perturbed questions, thus reducing annotation cost and enabling thorough evaluation of models’ performance on various semantic aspects. |
Question Answering as an Automatic Evaluation Metric for News Article Summarization (N19-1)
Copied to clipboard
| Challenge: | Recent work on summarization and headline generation focuses on maximizing ROUGE scores. |
| Approach: | They propose an extrinsic evaluation metric that maximizes ROUGE scores for automatic summarization and headline generation. |
| Outcome: | The proposed model maximizes ROUGE scores while increasing competitive results. |
Emptying the Ocean with a Spoon: Should We Edit Models? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study has questioned the use of direct model editing for factual corrections in LLMs. aaron s. de stefano, a sociologist, says that model editing is not a systematic remedy for factuality. |
| Approach: | They argue that direct model editing cannot be trusted as a remedy for LLM disadvantages . authors call for cautious promotion and application of model editing as part of LLM deployment process . |
| Outcome: | The proposed method is not trusted as a remedy for the disadvantages inherent to LLMs, the authors argue . they argue that it opens risks by reinforcing the notion that models can be trusted for factuality . |
Semantic Decomposition of Question and SQL for Text-to-SQL Parsing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text-to-SQL models for complex queries are limited by the syntactic complexity of SQL. |
| Approach: | They propose a question decomposition language that decomposes SQL queries into simple and regular sub-queries. |
| Outcome: | The proposed language decomposes SQL queries into simple and regular sub-queries . it is more accessible to non-experts for complex queries, enabling interpretable output . |
Data Efficient Masked Language Modeling for Vision and Language (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. |
| Approach: | They propose a masking strategy that masks tokens with a 15% probability for text-only data. |
| Outcome: | The proposed masking strategy outperforms the baseline model on a prompt-based probing task designed to elicit image objects. |