Better Surface Realization through Psycholinguistics
Bibliographic Data
| ID | 4810769 |
|---|---|
| Authors | Rajakrishnan Rajkumar (0000-0003-2052-4082, Indian Institute of Technology Indore), Michael White (0000-0001-7508-7882, The Ohio State University, corresponding author) |
| Year | 2014 |
| Volume | 8 |
| Issue | 10 |
| Pages | 428-448 |
| Publication date | 2014-10-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Language and Linguistics Compass (JOURNAL) |
| Journal identifiers | ISSN: 1749-818X • E-ISSN: 1749-818X |
| Publisher | Wiley (PUBLISHER • GB) |
| DOI | 10.1111/lnc3.12090 |
| OpenAlex | W1548207682 |
| Language | EN |
| Citations received | 3 |
| References cited | 51 |
In this survey, we review recent progress on surface realization in natural language generation (NLG), highlighting how machine learning models have moved beyondn-grams to successfully incorporate linguistic insights into increasingly rich models. We also advance the view that NLG still has much to gain by taking up insights from psycholinguistic studies - not only of human production but also of comprehension. We highlight how realization ranking models can be improved by modeling the role of memory in human language comprehension and discuss how surface realizers might transition to using grammars developed for incremental parsing in computational psycholinguistics, thereby making them more suitable for integration into real-time incremental dialog systems. From a production standpoint, we suggest that the principle ofuniform information densityhas the potential to enhance the theoretical basis for choice making in NLG and discuss two initial steps in this direction. Finally, we conclude our survey with a discussion of prospects for community-based evaluation of surface realization systems
Cognition · Linguistics · Natural language processing · Psycholinguistics · Computer Science · Mathematics · Natural Language Processing Techniques · Neuroscience · Philosophy · Psychology · Speech and dialogue systems · Topic Modeling
Incremental, Predictive Parsing with Psycholinguistically Motivated Tree-Adjoining Grammar
Locality and expectation effects in Hindi preverbal constituent ordering
A unified acoustic-to-speech-to-language embedding space captures the neural basis of natural language processing in everyday conversations
Speaking
Redundancy and reduction
Syntactic persistence in language production
Data from eye-tracking corpora as evidence for theories of syntactic processing complexity
Regulating mental energy
A probabilistic earley parser as a psycholinguistic model
An Activation‐Based Model of Sentence Processing as Skilled Memory Retrieval
Broken agreement
An Incremental Procedural Grammar for Sentence Formulation
An Integrated Theory of the Mind.
Towards a Probabilistic Version of Bidirectional OT Syntax and Semantics
Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models
Incremental, Predictive Parsing with Psycholinguistically Motivated Tree-Adjoining Grammar
Broad-Coverage Parsing Using Human-Like Memory Constraints
On the persistence of grammar in discourse formulas
The Syntactic Process
CCGbank
A multifactorial approach to adverb placement
Argument-Head Distance and Processing Complexity
| Citations per year | 0.23 |
|---|---|
| Citation span | 2013 - 2025 (13) |
| Highly cited | No |