Learning Interpretable Text Signals for Structured Responses

• URL: http://arxiv.org/abs/2606.25268v1
• Date: Wed, 24 Jun 2026 01:08:05 GMT
• Title: Learning Interpretable Text Signals for Structured Responses
• Abstract summary: This paper studies rating prediction as an initial case of interpretable text-response modelling.<n>We propose a joint non-negative matrix factorisation and binomial regression model, in which the document-topic representation is learned from both text reconstruction and rating prediction.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Textual data are often collected alongside structured response variables, but prediction and interpretation are commonly treated as separate tasks. This paper studies rating prediction as an initial case of interpretable text-response modelling, where the aim is to learn textual representations that are both semantically meaningful and aligned with an external response. We propose a joint non-negative matrix factorisation and binomial regression model, in which the document-topic representation is learned from both text reconstruction and rating prediction. Simulation experiments and a real-world review dataset show that the model can recover stable response-relevant textual signals and achieve competitive performance against linear and ridge regression baselines. The framework provides a practical step towards interpretable modelling of text-linked outcomes, with potential extensions to other response types beyond bounded ratings.

Related papers

• How Far Do Simple Transformations Translate Across Text Embedding Models? [1.7812673697676977]
  We investigate whether simple transformations can translate representations across heterogeneous text embedding models.<n>We test the hypothesis of latent universality in a realistic text setting beyond simplified benchmarks.<n>Overall, the results show that heterogeneous embedding spaces are not universally related by simple mappings as often suggested in some literature.
  arXiv  Detail & Related papers  (2026-08-06T12:57:01Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Inducing Causal Structure for Abstractive Text Summarization [76.1000380429553]
  We introduce a Structural Causal Model (SCM) to induce the underlying causal structure of the summarization data. We propose a Causality Inspired Sequence-to-Sequence model (CI-Seq2Seq) to learn the causal representations that can mimic the causal factors. Experimental results on two widely used text summarization datasets demonstrate the advantages of our approach.
  arXiv  Detail & Related papers  (2023-08-24T16:06:36Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)
• Bayesian Topic Regression for Causal Inference [3.9082355007261427]
  Causal inference using observational text data is becoming increasingly popular in many research areas. This paper presents the Bayesian Topic Regression model that uses both text and numerical information to model an outcome variable.
  arXiv  Detail & Related papers  (2021-09-11T16:40:43Z)
• On the Lack of Robust Interpretability of Neural Text Classifiers [14.685352584216757]
  We assess the robustness of interpretations of neural text classifiers based on pretrained Transformer encoders. Both tests show surprising deviations from expected behavior, raising questions about the extent of insights that practitioners may draw from interpretations.
  arXiv  Detail & Related papers  (2021-06-08T18:31:02Z)
• JST-RR Model: Joint Modeling of Ratings and Reviews in Sentiment-Topic Prediction [2.3834926671238916]
  We propose a probabilistic model to accommodate both textual reviews and overall ratings. The proposed method can enhance the prediction accuracy of review data and achieve an effective detection of interpretable topics and sentiments.
  arXiv  Detail & Related papers  (2021-02-18T15:47:34Z)
• Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning [11.205077315939644]
  We explore methods to generate query reformulations by training reformulators using text-to-text transformers. We apply policy-based reinforcement learning algorithms to further encourage reward learning. Our framework is demonstrated to be flexible, allowing reward signals to be sourced from different downstream environments.
  arXiv  Detail & Related papers  (2020-12-18T03:16:37Z)
• Understanding Neural Abstractive Summarization Models via Uncertainty [54.37665950633147]
  seq2seq abstractive summarization models generate text in a free-form manner. We study the entropy, or uncertainty, of the model's token-level predictions. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
  arXiv  Detail & Related papers  (2020-10-15T16:57:27Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)
• A Revised Generative Evaluation of Visual Dialogue [80.17353102854405]
  We propose a revised evaluation scheme for the VisDial dataset. We measure consensus between answers generated by the model and a set of relevant answers. We release these sets and code for the revised evaluation scheme as DenseVisDial.
  arXiv  Detail & Related papers  (2020-04-20T13:26:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.