Papers with learning methods
Bringing replication and reproduction together with generalisability in NLP: Three reproduction studies for Target Dependent Sentiment Analysis (C18-1)
Copied to clipboard
| Challenge: | a lack of reproducibility and generalisability is a major threat to scientific development in Natural Language Processing. |
| Approach: | They propose to use a model zoo to document and release language models and published code . they recommend that future replication experiments should consider a variety of datasets . |
| Outcome: | The proposed methods are compared on six English datasets and are based on the results. |
On The Ingredients of an Effective Zero-shot Semantic Parser (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have performed zero-shot learning by synthesizing training examples of canonical utterances and programs from a grammar, and further paraphrasing these utterrances to improve linguistic diversity. |
| Approach: | They propose to bridge gaps between canonical and real-world user-issued examples by using stronger paraphrasers and improved grammars. |
| Outcome: | The proposed model achieves strong performance on two semantic parsing benchmarks with zero labeled data. |
Learning with Contrastive Examples for Data-to-Text Generation (2020.coling-main)
Copied to clipboard
Yui Uehara, Tatsuya Ishigaki, Kasumi Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao
| Challenge: | Existing models for data-to-text generation generate fluent but sometimes incorrect sentences . Existing studies show that using contrastive examples improves the ability of generating sentences with better lexical choice without degrading the fluency. |
| Approach: | They propose to use models trained on incorrect sentences and learning methods that exploit contrastive examples to reduce such errors. |
| Outcome: | The proposed models generate fluent sentences but often have problematic ones in terms of correctness. |
Linguistically-driven Framework for Computationally Efficient and Scalable Sign Recognition (L18-1)
Copied to clipboard
| Challenge: | a new general framework for sign recognition from monocular video is presented . the framework exploits state-of-the-art learning methods while incorporating features based on what we know about the linguistic composition of lexical signs. |
| Approach: | They propose a general framework for sign recognition from monocular video . they exploit state-of-the-art learning methods while incorporating features from linguistic information . |
| Outcome: | The proposed framework exploits state-of-the-art learning methods while incorporating features based on what we know about linguistic composition of lexical signs. |
A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering (2021.acl-long)
Copied to clipboard
| Challenge: | Weakly supervised question answering usually has only final answers as supervision signals while correct solutions are not provided. |
| Approach: | They propose to explicitly exploit the semantic correlations between question-answer pairs and predicted answers by maximizing mutual information between question and answer pairs. |
| Outcome: | The proposed method significantly outperforms previous learning methods in terms of task performance and is more effective in training models to produce correct solutions. |
Evaluating Parameter Efficient Learning for Generation (2022.emnlp-main)
Copied to clipboard
Peng Xu, Mostofa Patwary, Shrimai Prabhumoye, Virginia Adams, Ryan Prenger, Wei Ping, Nayeon Lee, Mohammad Shoeybi, Bryan Catanzaro
| Challenge: | Parameter efficient learning methods (PERMs) are gaining attention for their ability to adapt to a downstream task. |
| Approach: | They propose to use parameter efficient learning methods to improve model adaptation . they compare in-domain evaluations and generalizations to unseen domains and new datasets . |
| Outcome: | The proposed method outperforms finetuning and PERMs in in-domain evaluations. |
TT-SI: Self-Improving LLM Agents with Test-Time Training (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for language model fine-tuning are expensive and inefficient . existing methods rarely assess whether a training sample provides novel information . |
| Approach: | They propose a test-time self-improvement algorithm that generates a sample that model struggles with . they also explore Test-Time Distillation, which leverages 'stronger supervisors' |
| Outcome: | The proposed algorithm improves performance with +5.48% absolute accuracy gain on average across benchmarks. |
Large Language Models are Miscalibrated In-Context Learners (2025.findings-acl)
Copied to clipboard
| Challenge: | In-context Learning and Supervised Fine-Tuning have emerged as pre-dominant methodologies for machine learning and NLP. |
| Approach: | They propose to use self-ensembling to improve both performance and calibration of language models. |
| Outcome: | The proposed learning paradigms can achieve better calibration and better performance than the previous learning paradigm. |
Exploring the Learning Capabilities of Language Models using LEVERWORLDS (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models of stochastic learning involve learning general structure rules and specific properties of the instance. |
| Approach: | They propose a framework that allows the generation of physics-inspired worlds that follow a similar generative process with different distributions and their instances can be expressed in natural language. |
| Outcome: | The proposed framework allows the generation of physics-inspired worlds that follow a similar generative process with different distributions and their instances can be expressed in natural language. |