Papers with LTR
Team SVMrank: Leveraging Feature-rich Support Vector Machines for Ranking Explanations to Elementary Science Questions (D19-53)
Copied to clipboard
| Challenge: | TextGraphs 2019 Shared Task on Multi-Hop Inference for Explanation Regeneration tackles explanation generation for elementary science questions. |
| Approach: | They propose a hybrid pipelined machine learning model and rule-based system to address MIER-19 . they use a featurerich learning-to-rank machine learning and a rule-driven system to rerank the LTR model predictions. |
| Outcome: | The proposed model was ranked fourth in the evaluation, close to the second and third ranked teams, achieving 39.4% MAP. |
On the Calibration and Uncertainty of Neural Learning to Rank Models for Conversational Search (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to rank documents in decreasing order of their probability of relevance are not well calibrated and have several sources of uncertainty. |
| Approach: | They propose to calibrate deterministic neural rankers for conversational search problems . they then use two techniques to model the uncertainty of neural ranker's uncertainty . |
| Outcome: | The proposed rankers output a predictive distribution of relevance as opposed to point estimates. |
Unsupervised Pivot Translation for Distant Languages (P19-1)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation (NMT) is a popular method for transferring information between languages. |
| Approach: | They propose an unsupervised pivot translation method which translates a language to a distant language through multiple hops. |
| Outcome: | The proposed method improves translation on 20 languages and 294 distant languages on 20 different languages and language pairs. |
DiAL : Diversity Aware Listwise Ranking for Query Auto-Complete (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Query Auto-Complete (QAC) is an essential search feature that helps users articulate their query by suggesting relevant completions as they type. |
| Approach: | They propose a new framework that explicitly optimizes for diversity alongside customer feedback signals to balance relevance and diversity. |
| Outcome: | The proposed framework yields an improvement of 8.5% in MRR and 22.8% in NDCG compared to the pairwise ranking approach on an eCommerce dataset. |
LiPO: Listwise Preference Optimization through Learning-to-Rank (2025.naacl-long)
Copied to clipboard
Tianqi Liu, Zhen Qin, Junru Wu, Jiaming Shen, Misha Khalman, Rishabh Joshi, Yao Zhao, Mohammad Saleh, Simon Baumgartner, Jialu Liu, Peter J Liu, Xuanhui Wang
| Challenge: | Recent work on language models with curated feedback provides promising alternatives to RLHF . multiple responses can be ranked by reward models or AI feedback, but there is no study on directly fitting upon a list of responses. |
| Approach: | They propose a method that aligns language models with curated human feedback . they propose SLiC and DPO as promising alternatives to traditional RLHF . |
| Outcome: | The proposed method outperforms DPO and SLiC on several preference alignment tasks with curated and real rankwise preference data. |
Methods, Applications, and Directions of Learning-to-Rank in NLP Research (2024.findings-naacl)
Copied to clipboard
| Challenge: | Learning-to-rank (LTR) algorithms aim to order items according to some criteria. |
| Approach: | They focus on the formal background of LTR and the most widely-used supervised methods . they also discuss how large language models are changing the LTR landscape . |
| Outcome: | The proposed methods are used in natural language processing and information retrieval tasks. |
Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Visual word sense disambiguation (VWSD) is a challenging task involving multiple candidates . context given for an ambiguous word is minimal, most often limited to a single word . |
| Approach: | They propose to use large language models to enhance given phrases and resolve ambiguity related to the target word. |
| Outcome: | The proposed frameworks improve the image representation of ambiguous words among candidates and achieve competitive ranking results. |
Learning to Rank Salient Content for Query-focused Summarization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Query-focused summarization (QFS) is gaining prominence in research community. |
| Approach: | They propose to integrate Learning-to-Rank (LTR) with Query-focused Summarization (QFS) to enhance the summary relevance via content prioritization. |
| Outcome: | The proposed model outperforms the state-of-the-art on QMSum benchmark and SQuALITY benchmark while offering a lower training overhead. |