Metraipolis › archive › dc_fccd463ec16b

Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts — arXiv:2609.00330

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00330
License (as archived)
CC0-1.0
Archived
2026-10-17T06:33:10.046Z
SHA-256 of the archived text
3a875152c369e09047b4cf540295f40164989120a160b55d70de648c12ed8b1b
Stable URL of this page
https://metraipolis.com/documento/dc_fccd463ec16b

How to cite

Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts — arXiv:2609.00330 — arXiv (en), https://arxiv.org/abs/2609.00330 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fccd463ec16b (Metraipolis archive dc_fccd463ec16b, sha256 3a875152c369e09047b4cf540295f40164989120a160b55d70de648c12ed8b1b)
BibTeX
@misc{dcfccd463ec16b,
  title = {Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts — arXiv:2609.00330},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00330},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fccd463ec16b; sha256 3a875152c369e09047b4cf540295f40164989120a160b55d70de648c12ed8b1b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00330. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In contact centers, real-time agent-assist tools determine, for each of many predefined topics, whether a live customer utterance is relevant and display a coaching card to the agent when it is. The input is noisy and challenging: ASR(Automatic Speech Recognition) transcripts of spontaneous phone conversations, which can be unclear, repetitive, and mostly lack punctuation. To systematically study this real-world task, we curate a human-annotated topic-utterance judgments dataset sourced from real call-center transcripts. We compare three types of matchers: a regex-based baseline, zero-shot sentence embedding encoders, and Gemini-based LLM matchers. In addition, two types of topic representations are studied in our benchmark:keyphrases and natural language description. Our empirical experiments highlight the superior performance of lightweight LLM matchers over embedding and regex models when equipped with natural language descriptions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00330 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.770Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).