Papers by Young-Suk Lee

11 papers
Learning Cross-Lingual IR from an English Retriever (2022.naacl-main)

Copied to clipboard

Challenge: DR.DECR is a cross-lingual information retrieval system trained using multi-stage knowledge distillation (KD) DRDECR demonstrates superior accuracy over direct fine-tuning with labeled CLIR data.
Approach: They propose a cross-lingual information retrieval system with multi-stage knowledge distillation . they teach powerful multilingual representations and CLIR by optimizing two corresponding KD objectives .
Outcome: The proposed system is the best single-model retriever on the XOR-TyDi benchmark . it is based on a multi-stage knowledge distillation process that can be expensive .
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches face challenges including complex question understanding and lack of large end-to-end training datasets.
Approach: They propose a modular knowledge base question answering system that leverages AMR parses for task-independent question understanding.
Outcome: The proposed system achieves state-of-the-art performance on two prominent KBQA datasets based on DBpedia.
Bootstrapping Multilingual AMR with Contextual Word Alignments (2021.eacl-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a sentence-level graph that is biased towards English.
Approach: They propose a technique for foreign-text-to-English AMR alignment using contextual word alignment between English and foreign language tokens.
Outcome: The proposed technique outperforms the best results for German, Italian, Spanish and Chinese.
Pushing the Limits of AMR Parsing with Self-Learning (2020.findings-emnlp)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsing has experienced a notable growth in performance in the last two years due to the impact of transfer learning and the development of novel architectures specific to AMR.
Approach: They propose to use AMR annotations to generate synthetic text and refine actions oracle without additional human annotations for AMR parsing.
Outcome: The proposed models improve on AMR 1.0 and 2.0 without human annotations.
Ensemble-Instruct: Instruction Tuning Data Generation with a Heterogeneous Mixture of LMs (2023.findings-emnlp)

Copied to clipboard

Challenge: Empirical studies with different instruction-tuned LMs show that our proposed method yields higher-quality instruction tuning data than Self-Instruct.
Approach: They propose to use in-context learning techniques to train strong conversational agents . they propose to categorize and simplify ICL templates to make prompt learning easier .
Outcome: Empirical results show that the proposed method yields higher-quality instruction tuning data than Self-Instruct and improves performance of both vanilla and instruction-tuned LMs.
A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering (2021.acl-short)

Copied to clipboard

Challenge: Existing knowledge base question answering systems do not leverage the explicit semantic parse of the question text.
Approach: They propose a transformer-based neural model that leverages the AMR semantic parse of a sentence.
Outcome: The proposed model outperforms the state-of-the-art on 4 popular benchmark datasets.
DocAMR: Multi-Sentence AMR Representation and Evaluation (2022.naacl-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) graphs are compared to gold graphs by the Smatch metric, but lack a well-defined representation and evaluation.
Approach: They propose an algorithm for deriving a unified graph representation using a super-sentential annotation method.
Outcome: The proposed algorithm avoids the pitfalls of over-merging and lacks coherence from under merging.
SYGMA: A System for Generalizable and Modular Question Answering Over Knowledge Bases (2022.findings-emnlp)

Copied to clipboard

Challenge: Knowledge Base Question Answering (KBQA) systems have limited generalizability across knowledge bases and multiple reasoning types.
Approach: They propose a modular approach for KBQA that is built on a framework adaptable to multiple knowledge bases and reasoning types.
Outcome: The proposed approach is generalized across multiple knowledge bases and reasoning types.
Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that pre-trained sequence-to-sequence Transformer models are effective in predicting linearized Abstract Meaning Representation graphs.
Approach: They propose a structure-aware transition-based approach to AMR parsing that integrates general pre-trained sequence-to-sequence language models with a structured transition set.
Outcome: The proposed approach retains the desirable properties of previous approaches while reaching the new parsing state of the art for AMR 2.0.
GPT-too: A Language-Model-First Approach for AMR-to-Text Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to generating text from AMRs focus on training sequence-to-sequence or graph-tosequent models on annotated data.
Approach: They propose a strong pre-trained language model with cycle consistency-based re-scoring to generate AMR text.
Outcome: The proposed model outperforms existing methods on the English LDC2017T10 dataset.
Maximum Bayes Smatch Ensemble Distillation for AMR Parsing (2022.naacl-main)

Copied to clipboard

Challenge: AMR parsing has experienced an unprecendented increase in performance in the last three years due to a mixture of effects including architecture improvements and transfer learning.
Approach: They propose to combine Smatch-based ensembling techniques with ensemble distillation to overcome this diminishing returns of silver data.
Outcome: The proposed technique can produce gains rivaling those of human annotated data for QALD-9 and achieve a new state-of-the-art for BioAMR.

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