Context-aware Information Extraction from Multi-thread Business Conversations
Bibliographic record
Abstract
This paper primarily focuses on developing an end-to-end solution which can process multi-threaded conversations and perform information extraction (IE) specific to a domain and intended business task. The challenges of IE in a conversation are a) context understanding, which consists of two elements: topic and sense of expression and b) establishing context flow. Since the target is free-flow dialogue, understanding the change in contexts is crucial. In this research, we attempt to build a solution that can infer and connect these contexts and reflect the same in the extracted information, taking care of things like negotiations. The proposed approach has three main steps; The first step is domain-dependent which performs topic classification at the sentence level. The second step is domain-independent, and it categorizes sentences into different semantic classes, to understand the conversation flow and parse it into multiple conversation threads. In the final step, we carry out morphological parsing to extract the target value, utilizing the predicted sentence class labels along with the conversation flow. A buyer-seller chat conversation is taken as the sample domain and the target IE is towards information for purchase order generation.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".