MétaCan
Menu
Back to cohort

Context-Driven Natural Language Understanding for Smarter Chatbot Responses

2025· article· W4416677478 on OpenAlexaff
Sunjhla Handa, Shanmugaraja Krishnasamy Venugopal, Madhusudana Kamballi, Amit Ojha, Ajay Shriram Kushwaha

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsCarleton University
Fundersnot available
KeywordsChatbotConversationNatural languageInferenceLanguage modelNatural language understandingScalabilityContext (archaeology)Language understanding

Abstract

fetched live from OpenAlex

The quality of chatbot responses in multi-turn conversations is improved by employing a context-driven natural language understanding (NLU) approach in this study. The system successfully records semantic relationships and speaker dynamics across conversation history by combining transformer-based models like BERT, GPT-2, T5 along with BART with hierarchical context encoders. Employing PyTorch along with HuggingFace on the high-performance configuration using NVIDIA A100 GPUs, the design is tuned for speed, relevance, and consistency. Hierarchical BERT+GPT-2 model achieves outstanding outcomes for BLEU (26.3), METEOR (22.1), BERTScore (0.889) along with F1 (0.81), coupled with strong user engagement, according to evaluation in datasets like MultiWOZ and PersonaChat. The significant performance-computational cost trade-off is shown in the study, which delves deeper into the effects of context embedding techniques, inference latency as well as and training efficiency. The significance of deep contextual modelling for developing conversational software with intelligence and human-like characteristics is highlighted by these results, which also provide a basis for future advancements with scalable along with adaptive dialogue systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.934
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.050
GPT teacher head0.342
Teacher spread0.292 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAI in Service InteractionsFrench-language works237,207