Papers by Shufan Wang

10 papers
Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism (N19-1)

Copied to clipboard

Challenge: Literary critics often attempt to uncover meaning in a single work of literature through careful reading and analysis.
Approach: They propose to use a literary theory to analyze Italo Calvino's novel Invisible Cities to leverage contextualized representations to embed each city's description and use unsupervised methods to cluster embeddings.
Outcome: The proposed method can be applied to Italo Calvino’s novel Invisible Cities . authors compare results to similarity judgments generated by human readers .
Robustness of Named-Entity Replacements for In-Context Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Modern large language models perform in-context learning, where query- answer demonstrations are shown before the final query.
Approach: They propose to use in-context learning to prompt queries before they are answered . they find that the choice of demonstrations can affect model performance .
Outcome: The proposed model performance improves on named entity replacements across three reasoning tasks and two popular LLMs.
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration (2021.emnlp-main)

Copied to clipboard

Challenge: Phrase representations derived from pretrained language models often lack lexical similarity to determine semantic relatedness.
Approach: They propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings by fine- tuning a dataset of diverse phrasal paraphrases and a large-scale dataset of phrases in context.
Outcome: The proposed model outperforms baseline models across phrase-level similarity tasks while also showing increased lexical diversity between nearest neighbors in the vector space.
kNN-LM Does Not Improve Open-ended Text Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Interpolation-based retrieval-augmented language models (LMs) are a subtype of retrieval augmented language model that computes the probability of the next token by interpolating between the softmax distribution of the original LM and a token distribution formed by retrieving over an external datastore.
Approach: They propose to interpolate the predicted distribution of the next word with a distribution formed from the most relevant retrievals for a given prefix.
Outcome: The proposed methods do not exhibit improvements in open-ended generation quality, as measured by automatic evaluation metrics and human evaluations.
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing datasets lack rich enough contexts to guide models and evaluations are unreliable for long-form creative text.
Approach: They propose a dataset and evaluation platform built from STORIUM . their dataset contains 6K lengthy stories with fine-grained natural language annotations .
Outcome: The proposed model can be used to generate 6K long stories with fine-grained natural language annotations and a user-generated dataset.
Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for ICD coding are limited due to the high-dimensional space of multi-label assignment and the long-tail challenge.
Approach: They propose a prompt-based fine-tuning technique with label semantics to solve this challenge.
Outcome: The proposed method outperforms state-of-the-art methods on a benchmark dataset of code assignment in 14.5% of cases.
Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing (2023.findings-emnlp)

Copied to clipboard

Challenge: In task-oriented semantic parsing, the system aims to translate users’ utterances in natural language to machine-interpretable programs (API calls) However, Large Language Models (LLMs) are known to hallucinate and therefore pose a formidable challenge in constraining generated content.
Approach: They propose to use large language models to translate user's utterances to machine-interpretable programs (API calls) they identify constraints violations in task-oriented utterrances and define fine-grained metrics that complement traditional ones.
Outcome: The proposed methods reduce constraints violations and improve quality of the generated API calls, but require careful consideration given their implementation complexity and latency.
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to improve embeddings from Mixture-of-Experts models allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity.
Approach: They propose an Adaptive Expert Allocation framework that performs layer-wise and token-wise expert allocation to enhance embedding quality.
Outcome: The proposed method improves embedding quality across multiple MoE models.
You can’t pick your neighbors, or can you? When and How to Rely on Retrieval in the kNN-LM (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that retrieval-enhanced language models can improve perplexity by combining text from large external datastores with a k-nearest neighbors model.
Approach: They propose a retrieval-enhanced language model that interpolates existing LMs with a k-nearest neighbors model and requires no additional training.
Outcome: The proposed model improves on two English language modeling datasets and shows that it is most effective when items have high semantic similarity with the query.
Modeling Exemplification in Long-form Question Answering via Retrieval (2022.naacl-main)

Copied to clipboard

Challenge: Exemplification is a process by which writers explain or clarify a concept by providing an example.
Approach: They propose to use a partially-written answer to query a large set of human-written examples extracted from a corpus to determine exemplification quality.
Outcome: The proposed model is able to retrieve human-written examples from a corpus and show that it is more relevant than state-of-the-art models.

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