Papers with neural language model

22 papers
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding (2020.emnlp-main)

Copied to clipboard

Challenge: Linguistic steganography studies how to hide secret messages in natural language cover texts.
Approach: They propose a method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model.
Outcome: The proposed method outperforms the state-of-the-art methods on four datasets by 15.3% and 38.9% in terms of bits/word and KL metrics.
Is Partial Linguistic Information Sufficient for Discourse Connective Disambiguation? A Case Study of Concession (2025.acl-srw)

Copied to clipboard

Challenge: Discourse relations are often not linguistically marked, but there are various connectives that explicitly signal discourse relations.
Approach: They analyze linguistic features that play an important role in disambiguation of polysemous connectives in Japanese by performing a neural language model.
Outcome: The proposed model performed well after removal of one of the two arguments that constitute the discourse relation, but significantly degraded disambiguation performance.
Sensei: Self-Supervised Sensor Name Segmentation (2021.findings-acl)

Copied to clipboard

Challenge: Sensor names are alphanumeric strings that encode key contextual information such as their function or physical location.
Approach: They propose a self-supervised framework that can learn to segment sensor names without human annotation.
Outcome: The proposed framework can learn to segment sensor names without human annotation on buildings.
How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation (N19-1)

Copied to clipboard

Challenge: Existing approaches to generate metaphors rely on template-based or rule-based knowledge, which constrains the diversity of generated metaphors.
Approach: They propose a neural approach to metaphor generation that uses wiki corpus to extract metaphorically used verbs and train a language model.
Outcome: The proposed approach generates metaphors with good readability and creativity using wiki corpus and automatic metrics and human evaluations.
Decipherment of Substitution Ciphers with Neural Language Models (D18-1)

Copied to clipboard

Challenge: Existing methods for deciphering homophonic substitution ciphers use pre-trained neural LMs.
Approach: They propose a beam search algorithm that scores the entire candidate plaintext at each step of the decipherment using a neural language model.
Outcome: The proposed beam search algorithm improves on challenging ciphers with smaller beam sizes and better error rates than state-of-the-art methods.
Evaluating pragmatic abilities of image captioners on A3DS (2023.acl-short)

Copied to clipboard

Challenge: Evaluating grounded neural language models with respect to pragmatic qualities such as truthfulness, contrastivity and overinformativity remains a challenge in absence of data collected from humans.
Approach: They propose to use an open source image-text dataset to evaluate pragmatic abilities of grounded neural language models with respect to pragmatic qualities such as truthfulness, contrastivity and over-informativity.
Outcome: The proposed model develops human-like pragmatic abilities with respect to truthfulness, contrastivity and over-informativity for specific features.
Multi-Word Lexical Simplification (2020.coling-main)

Copied to clipboard

Challenge: In text simplification, individual words are replaced with their simpler equivalents, but single word substitutions do not cover the full complexity of techniques humans use to approach text simulating.
Approach: They propose a task of multi-word lexical simplification in which a sentence is made easier to understand by replacing its fragment with a simpler alternative.
Outcome: The proposed method is based on a purpose-trained neural language model and evaluates against human and resource-based baselines.
Unsupervised Paraphrasability Prediction for Compound Nominalizations (2022.naacl-main)

Copied to clipboard

Challenge: Nominalizations can be difficult to interpret because of ambiguous semantic relations between deverbal noun and its arguments.
Approach: They propose to over-generate clausal paraphrases to predict whether a prenominal modifier can be re-written as a noun or adverb in a claual paraphrasability.
Outcome: The proposed method improves paraphrasability prediction and paraphrase generation in English . it shows that the prenominal modifier can be re-written as a noun or adverb in a clausal paraphrase .
Truncation Sampling as Language Model Desmoothing (2022.findings-emnlp)

Copied to clipboard

Challenge: Long samples of text from neural language models can be of poor quality.
Approach: They propose to think of a neural language model as a mixture of k and a true distribution that avoids infinite perplexity.
Outcome: The proposed methods generate more plausible long documents according to humans and break out of repetition.
Hidden Schema Networks (2023.acl-long)

Copied to clipboard

Challenge: Existing models that encode rich semantic and syntactic content are biased, but they are effective at encoding symbolic representations.
Approach: They propose a neural language model that enforces explicit relational structures which allow for compositionality onto the output representations of pretrained language models.
Outcome: The proposed model can encode sentences into sequences of symbols and infer the posterior distribution of the model from natural language datasets.
Towards Zero-shot Language Modeling (D19-1)

Copied to clipboard

Challenge: a number of natural questions have been asked about the inductive biases of neural networks on core NLP tasks.
Approach: They construct an informative prior for held-out languages on a task of character-level, open-vocabulary language modelling.
Outcome: The proposed model outperforms baseline models with an uninformative prior in both zero-shot and few-shot settings, showing that it is imbued with universal linguistic knowledge.
Discourse-Aware Soft Prompting for Text Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Recent advances in pre-trained langauge models (PLMs) have made great impact on text generation research.
Approach: They propose to use hierarchical blocking to simulate a higher-level discourse structure of human written text and attention sparsity to learn sparse transformations on the softmax-function.
Outcome: The proposed methods perform better on some generation tasks but don't generalize across all generation tasks.
Quantifying Adaptability in Pre-trained Language Models with 500 Tasks (2022.naacl-main)

Copied to clipboard

Challenge: a recent study examines the features and limits of LM adaptability to new tasks . many questions about the nature and limits remain unanswered .
Approach: They evaluate adaptability to new tasks using a new benchmark, TaskBench500 . they find adaptation procedures differ dramatically in their ability to memorize small datasets .
Outcome: The proposed benchmark compares 500 procedurally generated sequence modeling tasks to a new benchmark.
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding (2023.findings-acl)

Copied to clipboard

Challenge: In a task-oriented dialogue system, response generation is a conditional language model, but effective dialogue agents must balance fluent generation with stricter constraints.
Approach: They propose a rule-based content selection model that transduces a dialogue agent’s actions and their results into context-free grammars representing the space of contextually acceptable responses.
Outcome: The proposed architecture outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
PaLM: A Hybrid Parser and Language Model (D19-1)

Copied to clipboard

Challenge: Recent language models have shown strong data-fitting performance, but do not explicitly encode any notion of structural information.
Approach: They propose a hybrid parser and neural language model that adds an attention layer over text spans in the left context.
Outcome: The proposed model outperforms baseline models on language modeling and provides syntactically-informed representations of the context.
Solving Historical Dictionary Codes with a Neural Language Model (2020.emnlp-main)

Copied to clipboard

Challenge: a dictionary-based substitution code is common, but no automatic decipherment algorithms exist.
Approach: They propose a decoding lattice and a neural language model to solve word-based substitution codes . they apply their method to letters exchanged between general James Wilkinson and agents of the Spanish Crown .
Outcome: The proposed method decrypts letters written by general James Wilkinson and agents of the Spanish Crown in the late 1700s and early 1800s using a neural language model.
A Neural Model of Adaptation in Reading (D18-1)

Copied to clipboard

Challenge: Several studies suggest that readers do adapt their lexical and syntactic predictions to the current context.
Approach: They propose to add a simple adaptation mechanism to a neural language model to improve predictions of reading times.
Outcome: The proposed model improves predictions of human reading times compared to a non-adaptive model.
Automatic Nominalization of Clauses through Textual Entailment (2022.coling-1)

Copied to clipboard

Challenge: Past research on clause nominalization has focused on replacement of the head verb with a deverbal noun and resource development to support the task.
Approach: They propose to use a textual entailment model to optimize the position and POS of nominal arguments by fine-tuning a model on the task.
Outcome: The proposed model outperforms unsupervised approaches on the nominalization task and outperformed a state-of-the-art neural language model.
Can Sequence-to-Sequence Models Crack Substitution Ciphers? (2021.acl-long)

Copied to clipboard

Challenge: Current methods for deciphering historical ciphers use beam search and a neural language model . but, this approach assumes that the target plaintext language is known .
Approach: They propose an end-to-end multilingual decipherment model that can solve 1:1 substitution ciphers without explicit language identification.
Outcome: The proposed model can decipher text without explicit language identification while still being robust to noise.
Barack’s Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling (P19-1)

Copied to clipboard

Challenge: Existing language models are only capable of remembering facts seen at training time, and have difficulty recalling them.
Approach: They introduce a knowledge graph language model with mechanisms for selecting and copying facts from a Knowledge graph that are relevant to the context.
Outcome: The proposed model outperforms a baseline language model in generating factual knowledge and generating sentences that require factual information.
Neural Language Modeling for Named Entity Recognition (2020.coling-main)

Copied to clipboard

Challenge: Experimental results show that named entity recognition systems are faster and more flexible for the size of the corpus.
Approach: They propose to use a neural language model as an alternative to the conditional random field layer for named entity recognition.
Outcome: The proposed system has a significant speed advantage with a marginal performance degradation.
Connecting degree and polarity: An artificial language learning study (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies have shown that degree modifiers are related to sentence polarity, but they are not related to the grammatical number of an expression.
Approach: They propose to generalize degree modifiers to their polarity sensitivity in pre-trained language models by applying the Artificial Language Learning experimental paradigm from psycholinguistics to a neural language model.
Outcome: The proposed generalisations are consistent with existing linguistic observations that relate de-gree semantics to polarity sensitivity, including the main one: low degree semantics is associated with preference towards positive polarities.

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